{ "data": { "a": { "slug": "hy3", "name": "Hy3", "vendor": "Tencent (Hy team)", "vendorUrl": "https://aistudio.tencent.com", "kind": "weights", "category": "open-weights", "summary": "Hy3 is Tencent's open-weight mixture-of-experts language model, 295B parameters with 21B active, a 256K-token context and per-request reasoning effort, published on Hugging Face in BF16 and FP8 under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/hy3", "markdownUrl": "https://www.anchorterminal.com/tools/hy3.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/hy3.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/hy3.json", "dns": "hy3.grade.anchorterminal.com", "repo": "https://huggingface.co/tencent/Hy3", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "tencent/Hy3" }, { "registry": "huggingface", "name": "tencent/Hy3-FP8" }, { "registry": "huggingface", "name": "AngelSlim/Hy3-GGUF" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither tencent/Hy3 nor tencent/Hy3-FP8 is gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Running it yourself costs the hardware, 597.6 GB for the BF16 repository, 299.9 GB for FP8 and 89.4 GB for the smallest GGUF from Tencent's AngelSlim team (checked 2026-10-21).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-10-21).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-02" }, "docsUrl": "https://huggingface.co/tencent/Hy3", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "reasoning", "tool-calling", "apache-2.0", "safetensors", "fp8", "gguf", "self-hosted" ], "lastRelease": "2026-07-20", "graded": true, "anchor": { "graded": true, "score": 62.6, "grade": "B", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 22, "methodology": "0.7", "run": "2026-10-01", "scores": { "capability": 57, "interface": 75, "reach": 70, "risk": 60, "upkeep": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-11-02" }, "negative": 0, "verdict": "Hy3 is a 295B mixture-of-experts model with 21B active, trained for several tool calls a turn, with per-request reasoning effort and 256K of context. It needs an 8-GPU server for FP8 or about 200 GB for a 4-bit build. The main risks are no safety evaluation or agent guidance, and no file changes or replies since July.", "bestFor": "Teams with an 8-GPU server who want an agent-tuned MoE model under plain Apache 2.0", "strengths": [ "Plain Apache 2.0, downloadable with no account, safetensors only with a SHA-256 for every shard", "Model code in released Transformers, vLLM, SGLang and llama.cpp, with no remote code to run", "Several tool calls in one turn, and reasoning effort of no_think, low or high per request", "262,144 tokens of native context", "FP8 from Tencent and GPTQ-Int4 and GGUF builds from its AngelSlim team, and two live inference providers" ], "weaknesses": [ "597.6 GB in BF16, 299.9 GB in FP8 and 168.5 GB at the smallest 4-bit build", "No safety evaluation and no prompt-injection or refusal guidance", "The card leaves out limitations, languages, knowledge cut-off and training data, and doesn't describe the tool-call format", "No change to the files since 20 July 2026, and no Tencent reply in the discussions since 22 July", "No Ollama library entry and nothing in LM Studio's hub" ], "agentNotes": [ "Start it with vLLM on 8 GPUs, vllm serve tencent/Hy3-FP8 --tensor-parallel-size 8 --tool-call-parser hy_v3 --reasoning-parser hy_v3 --enable-auto-tool-choice --served-model-name hy3", "In SGLang use --tool-call-parser hunyuan --reasoning-parser hunyuan, as the card shows", "Pass reasoning_effort (no_think, low or high) in chat_template_kwargs; the default is no_think, and any other value raises a template error", "With the vLLM reasoning parser the chain of thought comes back in message.reasoning and the answer in message.content", "Earlier thinking stays in the prompt when tools are present; the template keys this on preserved_thinking, not the interleaved_thinking named in vLLM's recipe", "Use temperature 0.9 and top_p 1.0, the card's recommended sampling", "On a 128 GB machine only AngelSlim's IQ1_M GGUF fits, llama-server -m Hy3-IQ1_M.gguf -ctk q8_0 -ctv q8_0 -fa on -c 65536, with llama.cpp b11768 or later; at 89.4 GB × 1.2 it sits right at the 107.4 GB ceiling, so shorten the context if it fails to load, and expect a 1-bit build to fall short of Tencent's numbers", "Without the hardware, call it through Featherless AI or DeepInfra via Hugging Face's inference providers" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 2.8, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "B", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 62.6 } ], "editorialScores": { "capability": 57, "interface": 75, "reach": 70, "risk": 60, "upkeep": 56 }, "provenanceScore": 63, "checked": { "categories": { "capability": "2026-11-02", "interface": "2026-11-02", "reach": "2026-11-02", "risk": "2026-11-02", "upkeep": "2026-11-02" }, "last": "2026-11-02", "oldest": "2026-11-02", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# Tencent's command from the card (8 GPUs, H20-3e or larger)\nvllm serve tencent/Hy3 --tensor-parallel-size 8 \\\n --tool-call-parser hy_v3 --reasoning-parser hy_v3 \\\n --enable-auto-tool-choice --served-model-name hy3\n# or AngelSlim's IQ1_M GGUF (89.4 GB) with llama.cpp:\nllama-server -m Hy3-IQ1_M.gguf -ctk q8_0 -ctv q8_0 -fa on -c 65536", "http": "curl http://localhost:8000/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\"model\": \"hy3\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}], \"temperature\": 0.9, \"top_p\": 1.0, \"chat_template_kwargs\": {\"reasoning_effort\": \"high\"}}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/hy3" }, "sameCompany": [ "hy-memory", "tencentdb-agent-memory", "hunyuanocr", "hy-memory-30b-a3b", "wevisone-vl-2b", "wevisone-vl-4b" ], "weights": { "trainedBy": "Tencent (Hy team)", "params": "295B", "active": "21B", "context": 262144, "goodFor": "Mixture-of-experts language model with tool calling and per-request reasoning effort (off by default), text only.", "runtimes": [ "llama.cpp", "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Hy3-Q2_K_XL", "url": "https://huggingface.co/AngelSlim/Hy3-GGUF/blob/main/Hy3-Q2_K_XL.gguf", "who": "AngelSlim", "precision": "q2_k_xl", "sizeGB": 100.1, "memoryGB": 128, "format": "gguf", "runsOn": [ "llama.cpp (Vulkan)", "llama.cpp (ROCm)" ], "note": "From Tencent's AngelSlim compression project; a -mtp variant of each file adds the MTP layer" }, { "name": "Hy3-IQ1_M", "url": "https://huggingface.co/AngelSlim/Hy3-GGUF/blob/main/Hy3-IQ1_M.gguf", "who": "AngelSlim", "precision": "iq1_m", "sizeGB": 89.4, "memoryGB": 128, "format": "gguf", "runsOn": [ "llama.cpp (Vulkan)", "llama.cpp (ROCm)" ], "note": "From Tencent's AngelSlim compression project; a -mtp variant of each file adds the MTP layer" }, { "name": "Hy3-Q3_K_M", "url": "https://huggingface.co/AngelSlim/Hy3-GGUF/blob/main/Hy3-Q3_K_M.gguf", "who": "AngelSlim", "precision": "q3_k_m", "sizeGB": 134.6, "memoryGB": 192, "format": "gguf", "runsOn": [ "llama.cpp (Vulkan)", "llama.cpp (ROCm)" ], "note": "From Tencent's AngelSlim compression project; a -mtp variant of each file adds the MTP layer" }, { "name": "Hy3-Q4_K_M", "url": "https://huggingface.co/AngelSlim/Hy3-GGUF/blob/main/Hy3-Q4_K_M.gguf", "who": "AngelSlim", "precision": "q4_k_m", "sizeGB": 182.3, "memoryGB": 256, "format": "gguf", "runsOn": [ "llama.cpp (Vulkan)", "llama.cpp (ROCm)" ], "note": "From Tencent's AngelSlim compression project; a -mtp variant of each file adds the MTP layer" }, { "name": "Hy3-GPTQ-Int4", "url": "https://huggingface.co/AngelSlim/Hy3-GPTQ-Int4", "who": "AngelSlim", "precision": "gptq-int4", "sizeGB": 168.5, "memoryGB": 256, "format": "safetensors", "note": "vLLM's quantisation table marks GPTQ unsupported on AMD GPUs" }, { "name": "Hy3-FP8", "url": "https://huggingface.co/tencent/Hy3-FP8", "who": "publisher", "precision": "fp8", "sizeGB": 299.9, "memoryGB": 512, "format": "safetensors" }, { "name": "Hy3", "url": "https://huggingface.co/tencent/Hy3", "who": "publisher", "precision": "bf16", "sizeGB": 597.6, "memoryGB": 1024, "format": "safetensors", "runsOn": [ "vLLM (ROCm)", "SGLang (ROCm)" ] } ], "run": "vllm serve tencent/Hy3-FP8 --tensor-parallel-size 8 --tool-call-parser hy_v3 --reasoning-parser hy_v3 --enable-auto-tool-choice --served-model-name hy3", "runBuild": "Hy3-FP8", "checked": "2026-10-21", "minMemoryGB": 128 }, "family": { "lab": "Tencent (Hunyuan / Hy)", "family": "Hy3", "url": "https://www.anchorterminal.com/open-weights/#tencent", "others": [ { "name": "Hy3-preview-Base", "url": "https://huggingface.co/tencent/Hy3-preview-Base", "params": "295B total, 21B activated (+3.8B MTP)" }, { "name": "Hy3-preview", "url": "https://huggingface.co/tencent/Hy3-preview", "params": "295B total, 21B activated (+3.8B MTP)" } ], "olderCount": 22, "unrestrictedCopies": 5 }, "area": "models", "provenance": { "legalEntity": "Tencent (named in the LICENSE file's copyright line)", "domain": "tencent.com", "domainRegistered": "1998-09-14", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The LICENSE file reads Copyright (C) 2026 Tencent above the Apache 2.0 text. No fuller legal name was found.", "The card's official website is aistudio.tencent.com (Hy AI Studio). RDAP at Verisign gives tencent.com a registration date of 14 September 1998.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "No changelog. The Hugging Face commit messages are mostly uploads; the last change, on 20 July 2026, added a dtype line to config.json.", "security.txt answered 404 on www.tencent.com, and aistudio.tencent.com answers /.well-known/security.txt with its web app, so there is none." ], "score": 63 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hy3.json", "live": { "slug": "hy3", "securityTxt": { "url": "https://tencent.com/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-11-10T16:08:29.745986156Z" }, "domain": { "domain": "tencent.com", "registered": "1998-09-14", "source": "https://rdap.verisign.com/com/v1/domain/tencent.com", "checkedAt": "2026-11-08T14:51:09.863578494Z" }, "updatedAt": "2026-11-10T16:08:29.745986156Z" } }, "answer": "Hy3 scores 62.6 (B) on agent readiness against LFM3-1.7B's 61 (C), and leads in 1 of 4 scored categories. LFM3-1.7B leads on reach, agent interface and documentation and upkeep.", "b": { "slug": "lfm3-1-7b", "name": "LFM3-1.7B", "vendor": "Liquid AI", "vendorUrl": "https://www.liquid.ai", "kind": "weights", "category": "open-weights", "summary": "LFM3-1.7B is Liquid AI's open-weight 1.73B text model for on-device agents, with tool calling, deferred tools, switchable thinking and a 256K-token context, released on 27 October 2026 with Liquid's own GGUF, FP8, NVFP4, MLX and ONNX builds.", "url": "https://www.anchorterminal.com/tools/lfm3-1-7b", "markdownUrl": "https://www.anchorterminal.com/tools/lfm3-1-7b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/lfm3-1-7b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/lfm3-1-7b.json", "dns": "lfm3-1-7b.grade.anchorterminal.com", "repo": "https://huggingface.co/LiquidAI/LFM3-1.7B", "license": "LFM Open License v1.0 (free commercial use below $10M annual revenue)", "transports": [], "packages": [ { "registry": "huggingface", "name": "LiquidAI/LFM3-1.7B" }, { "registry": "huggingface", "name": "LiquidAI/LFM3-1.7B-GGUF" }, { "registry": "huggingface", "name": "LiquidAI/LFM3-1.7B-MLX-4bit" }, { "registry": "ollama", "name": "lfm3" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The repository and Liquid's GGUF, MLX and ONNX repositories are not gated (checked 2026-11-10).", "pricing": "free", "pricingNotes": "Free to download and use under the LFM Open License v1.0, commercial use included for organisations with under $10M in annual revenue; above that, commercial use isn't licensed. Running it yourself costs little hardware, 1.10 GB for Liquid's Q4_K_M GGUF and 3.46 GB in BF16. Liquid's API also serves it, at prices shown in its console (checked 2026-11-10).", "priceSummary": "Free", "where": "local", "x402": { "level": "no", "evidence": "Weights you download and run yourself, so there is nothing to pay per call and no payment protocol (checked 2026-11-10).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-11-10" }, "docsUrl": "https://docs.liquid.ai/lfm/models/lfm3-1.7b", "llmsTxt": "https://docs.liquid.ai/llms.txt", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "small", "edge", "reasoning", "tool-calling", "long-context", "custom-licence", "safetensors", "gguf", "mlx", "onnx", "self-hosted" ], "lastRelease": "2026-11-09", "graded": true, "anchor": { "graded": true, "score": 61, "grade": "C", "agentReady": false, "rank": 0, "ranked": false, "notRankedWhy": "An open-weight model, graded by the open-weight checklist and ranked among open-weight models, not against tools", "rankOf": 1518, "categoryRank": 55, "methodology": "0.7", "run": "2026-10-01", "scores": { "interface": 100, "reach": 85, "risk": 40, "upkeep": 67 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-11-10" }, "negative": 0, "verdict": "A 1.73B model that fits an 8 GB machine with room to spare, with a documented tool-call format, deferred tools, a thinking switch and a 256K context. It runs today in llama.cpp, Ollama and LM Studio only, loads in Transformers through repository code, and has no safety results, security contact or data sources.", "bestFor": "Agents on a laptop, phone or small server that need tool calling and a long context from a model under 2 GB at 4 bits", "strengths": [ "Fits an 8 GB machine from Liquid's own GGUF, at 1.10 GB for Q4_K_M", "The card and docs document the tool-call format, deferred tools and tool search", "A 256K-token context, trained in mid-training per the card", "Thinking can be turned off per request", "Liquid's own API serves it, and its guide documents JSON Schema output" ], "weaknesses": [ "vLLM and SGLang have no released support, though the card lists both", "Loading in Transformers runs code from the repository", "No safety results and no security contact", "Liquid says turning thinking off can be inconsistent", "The licence stops free commercial use at $10M in annual revenue", "Training data is described without sources or a cut-off" ], "agentNotes": [ "Start it with `llama-server -hf LiquidAI/LFM3-1.7B-GGUF:Q4_K_M --jinja` or `ollama run lfm3`", "Use temperature 0.1, top_k 50 and repetition penalty 1.1 for chat, tools and agents, per the card", "Pass `enable_thinking=False` for direct answers, and expect it to reason anyway on hard tasks", "For a large tool catalogue mark tools `defer_loading` and give it a search tool", "Don't plan on vLLM or SGLang until a release carries LFM3", "Liquid doesn't recommend it for agentic coding or complex multi-step reasoning" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.7", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 100, "reach": 85, "risk": 40, "upkeep": 67 }, "provenanceScore": 73, "checked": { "categories": { "interface": "2026-11-10", "reach": "2026-11-10", "risk": "2026-11-10", "upkeep": "2026-11-10" }, "last": "2026-11-10", "oldest": "2026-11-10", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "llama-server -hf LiquidAI/LFM3-1.7B-GGUF:Q4_K_M --jinja\n# or\nollama run lfm3", "http": "curl http://localhost:8080/v1/chat/completions \\\n -H 'Content-Type: application/json' \\\n -d '{\"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}]}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/lfm3-1-7b" }, "sameCompany": [ "liquid-d1", "lfm2-5-2-6b", "lfm3-audio-2b", "lfm3-omni-2b", "lfm3-vl-2b" ], "weights": { "trainedBy": "Liquid AI", "builtOn": "LiquidAI/LFM3-1.7B-Base", "params": "1.73B", "context": 262144, "goodFor": "Small on-device agent model for tool calling, tool search over large catalogues, structured output and long-context work on a laptop or phone, not for agentic coding or complex multi-step reasoning.", "runtimes": [ "llama.cpp", "Ollama", "LM Studio" ], "builds": [ { "name": "LFM3-1.7B", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B", "who": "publisher", "precision": "bf16", "sizeGB": 3.46, "memoryGB": 8, "format": "safetensors", "runsOn": [ "Transformers" ], "note": "Loads in Transformers with the repository's own code. Liquid also publishes FP8 (2.21 GB) and NVFP4 (1.83 GB) safetensors builds, which the card pairs with SGLang, and an ONNX repository" }, { "name": "LFM3-1.7B-GGUF Q8_0", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B-GGUF", "who": "publisher", "precision": "q8_0", "sizeGB": 1.85, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp", "LM Studio" ] }, { "name": "LFM3-1.7B-GGUF Q4_K_M", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B-GGUF", "who": "publisher", "precision": "q4_k_m", "sizeGB": 1.1, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp", "LM Studio" ], "note": "LFM3-1.7B-Q4_K_M.gguf, from the Hub's file list. The repository also holds a quantisation-aware LFM3-1.7B-QAD-Q4_0.gguf (1.05 GB), Q8_0, F16 and BF16 files" }, { "name": "LFM3-1.7B-MLX-4bit", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B-MLX-4bit", "who": "publisher", "precision": "4bit", "sizeGB": 0.97, "memoryGB": 8, "format": "mlx", "runsOn": [ "MLX" ], "note": "Liquid also publishes 5, 6 and 8-bit and BF16 MLX builds" }, { "name": "ollama lfm3", "url": "https://ollama.com/library/lfm3", "who": "ollama", "precision": "q4_k_m", "sizeGB": 1.1, "memoryGB": 8, "format": "ollama", "runsOn": [ "Ollama" ], "note": "Ollama's library build, size as its tags page shows it on 10 November 2026. The library also has q8_0, bf16, mxfp8 and nvfp4 tags" } ], "run": "llama-server -hf LiquidAI/LFM3-1.7B-GGUF:Q4_K_M --jinja", "runBuild": "LFM3-1.7B-GGUF Q4_K_M", "checked": "2026-11-10", "minMemoryGB": 8 }, "family": { "lab": "Liquid AI", "family": "LFM3", "url": "https://www.anchorterminal.com/open-weights/#liquid", "others": [ { "name": "LFM3-1.7B-Base", "url": "https://huggingface.co/LiquidAI/LFM3-1.7B-Base", "params": "1.73B" }, { "name": "LFM3-VL-2B", "url": "https://huggingface.co/LiquidAI/LFM3-VL-2B", "params": "1.92B", "listing": "https://www.anchorterminal.com/tools/lfm3-vl-2b" }, { "name": "LFM3-Omni-2B", "url": "https://huggingface.co/LiquidAI/LFM3-Omni-2B", "params": "2.17B", "listing": "https://www.anchorterminal.com/tools/lfm3-omni-2b" }, { "name": "LFM3-Audio-2B", "url": "https://huggingface.co/LiquidAI/LFM3-Audio-2B", "params": "2.00B", "listing": "https://www.anchorterminal.com/tools/lfm3-audio-2b" } ] }, "area": "models", "provenance": { "legalEntity": "Liquid AI, Inc. (the licensor named in the LFM Open License)", "domain": "liquid.ai", "domainRegistered": "2017-12-16", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/LiquidAI/LFM3-1.7B/commits/main", "securityTxt": "none", "checked": "2026-11-10", "notes": [ "The licence names Liquid AI, Inc. as licensor. The domain's registration date is as recorded on the liquid-d1 listing on 8 October 2026", "www.liquid.ai/.well-known/security.txt answered 404 on 10 November 2026" ], "score": 73 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/lfm3-1-7b.json" }, "edges": [ { "by": 25, "category": "interface", "leads": "lfm3-1-7b", "name": "Agent interface", "reasons": { "a": "The chat template earns 20, a chat_template.jinja in the repository. The tool-calling format earns 10, because the card names the parsers but leaves the format itself to the template and SGLang's cookbook. Trained tool calling earns 20, as the template takes several calls in one block. Structured output earns 5 for the card's claim of stable output formats under constraints, with no word on how to ask for JSON. Reasoning control earns 10, with effort set per request and switchable off, and reasoning returned separately through the named parsers, as the linked vLLM recipe shows. Context earns 10 for 262,144 tokens native.", "b": "Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, tools, deferred tools, tool results and the thinking switch. Tool-calling format 25, the card and Liquid's tool-use page document tools passed through `tools=` in apply_chat_template, calls returned as XML and results sent back as tool messages. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so several calls fit in one turn, and the card says the model was trained on tool calls and agentic traces and with reinforcement learning inside agent harnesses. Structured output 15, Liquid's API guide documents `response_format` with a JSON Schema, with lfm3-1.7b as the model in its examples, and says the schema is checked before generation starts. Reasoning control 10, the card documents `enable_thinking=False` in the chat template to turn reasoning off per request, with reasoning on by default inside think tags, and `preserve_thinking` for earlier turns. Context 10, 256K tokens per the card, which says the mid-training stage extended the context window to 256K, and max_position_embeddings 262144 in config.json. 20 + 25 + 20 + 15 + 10 + 10 = 100." }, "scores": { "a": 75, "b": 100 } }, { "by": 20, "category": "risk", "leads": "hy3", "name": "Risk", "reasons": { "a": "File safety earns the full 25, safetensors only with no pickle files, and the documented route runs vLLM or SGLang from their own code with a Jinja template, so nothing from the repository runs at load or prompt time. Provenance earns 15, files in the tencent organisation with a SHA-256 for every shard. Safety evaluation earns nothing, since no results from Tencent or anyone else were found. Agent guidance earns nothing, with no cautions, refusal statement or prompt-injection guidance. Licence risk keeps all 15 under plain Apache 2.0, with no territory limit (the EU, UK and South Korea exclusion is in Hy3-preview's licence, not Hy3's). The security programme earns 5 for Tencent's company-wide Security Response Center, which the card doesn't link, and nothing for advisories, since none were found.", "b": "File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, files in the LiquidAI organisation, which Liquid's docs page for the model and its blog post link to (10). Safety evaluation 0, no safety results on the card or in Liquid's blog post for the LFM3 family, neither of which mentions safety testing. Agent guidance 0, Nothing on prompt injection, an instruction hierarchy, what refusals cover or safeguards to add. Licence risk 10, 15 less 5 for the $10M annual revenue threshold on commercial use. Security programme 0, no way to report a flaw found. 15 + 15 + 0 + 0 + 10 + 0 = 40." }, "scores": { "a": 60, "b": 40 } }, { "by": 15, "category": "reach", "leads": "lfm3-1-7b", "name": "Reach", "reasons": { "a": "Memory earns 5, because the smallest build of 4-bit precision or better is AngelSlim's GPTQ-Int4 of 168.5 GB, about 202 GB with the fifth added, which is within 256 GB but beyond any single workstation. The 1-bit IQ1_M GGUF fits our reference machine but sits below the 4-bit line. Runtimes earn 20, for model code in released Transformers, vLLM, SGLang and llama.cpp; Ollama and LM Studio have no entry for it. Builds earn the full 15, with Tencent's FP8 repository and AngelSlim's GPTQ and GGUF builds. Terms earn 15 for plain Apache 2.0. Download earns 10, with no gate and no account. Hosted earns 5, since Featherless AI and DeepInfra serve it live through Hugging Face.", "b": "Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB, and 1.10 GB × 1.2 = 1.3 GB, which fits 8 GB, well inside the 16 GB line. Runtimes 15, Released llama.cpp has the lfm3 architecture (src/models/lfm3.cpp at b12242), Ollama's library has an lfm3 entry, and LM Studio's catalogue runs the architecture (its liquid/lfm3-vl-2b entry; lmstudio-community publishes a GGUF of this model). Builds 15, Liquid's GGUF repository holds Q4_0, Q4_K_M, Q8_0, F16 and BF16 files, and Liquid publishes 4-bit and 8-bit MLX builds and an ONNX repository, all in the LiquidAI organisation. Terms 10, the LFM Open License v1.0, a custom licence that lets anyone use it commercially for free below a threshold of $10M annual revenue. Download 10, the Hub API reports gated false for the model and its GGUF, MLX and ONNX repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Liquid's own API lists lfm3-1.7b among its models, so the publisher hosts it. 30 + 15 + 15 + 10 + 10 + 5 = 85." }, "scores": { "a": 70, "b": 85 } }, { "by": 11, "category": "upkeep", "leads": "lfm3-1-7b", "name": "Documentation and upkeep", "reasons": { "a": "The model card earns 11, covering intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off. Training data earns 5 for a general statement with no cut-off. The last change earns 10, a config.json edit on 20 July and AngelSlim uploads on 21 July, within 180 days on 2 November 2026; the line drops to 5 after 17 January 2027 unless the files change. Responsiveness earns 10, with Tencent replies on 7 of 19 discussions and none since 22 July. Version policy earns the full 10, since the preview stays in its own repository and the card dates it and says what changed. File health earns 10, with files that agree and no broken-file report waiting.", "b": "Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), a limitation (not recommended for agentic coding or complex multi-step reasoning), architecture (24 layers: 13 gated short convolutions, 5 sliding-window and 6 global attention), parameters (1.73B), context (256K) and 16 languages. Training data 5, A general description: 22T tokens of pre-training in two stages with the kinds of data added since LFM2, 1.75T tokens of supervised fine-tuning, then mixed reinforcement learning, distillation from six specialist teachers and agentic reinforcement learning. Last change 20, the last commit, on 9 November 2026, added the OpenVINO checkpoint to the card's inference table, a day before this check. Responsiveness 10, Of the 22 discussions that aren't pull requests (27 October to 8 November 2026), 7 have a reply from a LiquidAI member, which is some. Version policy 5, LFM3 came out in new repositories and the LFM2.5 models stay in theirs. File health 10, Config, template and card agree on the lfm3 architecture, the 262,144-token context and the thinking switch. 17 + 5 + 20 + 10 + 5 + 10 = 67." }, "scores": { "a": 56, "b": 67 } } ], "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Tencent (Hy team)", "b": "Liquid AI", "name": "Vendor" }, { "a": "no (local only)", "b": "no (local only)", "name": "Hosted endpoint" }, { "a": "", "b": "", "name": "Transports" }, { "a": "None", "b": "None", "name": "Auth" }, { "a": "Free", "b": "Free", "name": "Pricing" }, { "a": "no", "b": "no", "name": "x402" }, { "a": "Apache-2.0", "b": "LFM Open License v1.0 (free commercial use below $10M annual revenue)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "yes", "name": "llms.txt" }, { "a": "2026-07-20", "b": "2026-11-09", "name": "Last release" }, { "a": "no document linked", "b": "no document linked", "name": "Terms last updated" }, { "a": "no document linked", "b": "no document linked", "name": "Privacy policy last updated" }, { "a": "2.8/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Hy3 scores 62.6 (B) on agent readiness against LFM3-1.7B's 61 (C), and leads in 1 of 4 scored categories. LFM3-1.7B leads on reach, agent interface and documentation and upkeep.", "question": "Which is better for AI agents, Hy3 or LFM3-1.7B?" } ], "goodFor": [ { "aheadOn": [ "Risk, 60 against 40" ], "also": null, "goodFor": "Teams with an 8-GPU server who want an agent-tuned MoE model under plain Apache 2.0", "slug": "hy3", "watchFor": "597.6 GB in BF16, 299.9 GB in FP8 and 168.5 GB at the smallest 4-bit build" }, { "aheadOn": [ "Reach, 85 against 70", "Agent interface, 100 against 75", "Documentation and upkeep, 67 against 56" ], "also": null, "goodFor": "Agents on a laptop, phone or small server that need tool calling and a long context from a model under 2 GB at 4 bits", "slug": "lfm3-1-7b", "watchFor": "vLLM and SGLang have no released support, though the card lists both" } ], "history": null, "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-hy3.json", "title": "Agents-A1-4B vs Hy3", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-lfm3-1-7b.json", "title": "Agents-A1-4B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-hy3.json", "title": "Apertus v1.5 8B vs Hy3", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lfm3-1-7b.json", "title": "Apertus v1.5 8B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-hy3.json", "title": "Apodex-1.1-mini vs Hy3", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lfm3-1-7b.json", "title": "Apodex-1.1-mini vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-hy3.json", "title": "Arete-27B vs Hy3", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/arete-27b-vs-lfm3-1-7b.json", "title": "Arete-27B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/arete-27b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-hy3.json", "title": "BigBang-v1 vs Hy3", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-lfm3-1-7b.json", "title": "BigBang-v1 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-hy3.json", "title": "Carbon-X vs Hy3", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-lfm3-1-7b.json", "title": "Carbon-X vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-hy3.json", "title": "Cola2 vs Hy3", "url": "https://www.anchorterminal.com/compare/cola2-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/cola2-vs-lfm3-1-7b.json", "title": "Cola2 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/cola2-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-hy3.json", "title": "Cosmos-Reason2-2B vs Hy3", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lfm3-1-7b.json", "title": "Cosmos-Reason2-2B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-hy3.json", "title": "Darwin-36B-Opus vs Hy3", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lfm3-1-7b.json", "title": "Darwin-36B-Opus vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3.json", "title": "DeepSeek-V3.2 vs Hy3", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm3-1-7b.json", "title": "DeepSeek-V3.2 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-hy3.json", "title": "DeepSeek V4.1 Flash vs Hy3", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lfm3-1-7b.json", "title": "DeepSeek V4.1 Flash vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-hy3.json", "title": "DeepSeek-V4-Flash-0731 vs Hy3", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-1-7b.json", "title": "DeepSeek-V4-Flash-0731 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.json", "title": "Devstral Small 2 vs Hy3", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b.json", "title": "Devstral Small 2 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-hy3.json", "title": "DiffusionGemma 26B A4B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm3-1-7b.json", "title": "DiffusionGemma 26B A4B IT vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-hy3.json", "title": "EXAONE 4.5 33B vs Hy3", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-lfm3-1-7b.json", "title": "EXAONE 4.5 33B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-hy3.json", "title": "Gemma 4 12B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm3-1-7b.json", "title": "Gemma 4 12B IT vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-hy3.json", "title": "Gemma 4 26B A4B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lfm3-1-7b.json", "title": "Gemma 4 26B A4B IT vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-hy3.json", "title": "Gemma 4 31B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lfm3-1-7b.json", "title": "Gemma 4 31B IT vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-hy3.json", "title": "Gemma 4 E2B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lfm3-1-7b.json", "title": "Gemma 4 E2B IT vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-hy3.json", "title": "Gemma 4 E4B IT vs Hy3", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lfm3-1-7b.json", "title": "Gemma 4 E4B IT vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-hy3.json", "title": "GLM-4.5-Air vs Hy3", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-lfm3-1-7b.json", "title": "GLM-4.5-Air vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-hy3.json", "title": "GLM-4.7-Flash vs Hy3", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lfm3-1-7b.json", "title": "GLM-4.7-Flash vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy3.json", "title": "GLM-5.3-Flash vs Hy3", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-1-7b.json", "title": "GLM-5.3-Flash vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-hy3.json", "title": "GLM-5.3 vs Hy3", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-1-7b.json", "title": "GLM-5.3 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-hy3.json", "title": "gpt-oss-120b vs Hy3", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lfm3-1-7b.json", "title": "gpt-oss-120b vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3.json", "title": "gpt-oss-20b vs Hy3", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-1-7b.json", "title": "gpt-oss-20b vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-hy3.json", "title": "Granite 4.2 30B vs Hy3", "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-lfm3-1-7b.json", "title": "Granite 4.2 30B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/granite-4-2-30b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-hy3.json", "title": "Granite 4.2 3B vs Hy3", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lfm3-1-7b.json", "title": "Granite 4.2 3B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-hy3.json", "title": "Granite 4.2 8B vs Hy3", "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-lfm3-1-7b.json", "title": "Granite 4.2 8B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/granite-4-2-8b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-hy3.json", "title": "Hy-Memory-30B-A3B vs Hy3", "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-hy3" }, { "json": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-lfm3-1-7b.json", "title": "Hy-Memory-30B-A3B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-inkling.json", "title": "Hy3 vs Inkling", "url": "https://www.anchorterminal.com/compare/hy3-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-inkling-small.json", "title": "Hy3 vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/hy3-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Hy3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/hy3-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-kimi-k3.json", "title": "Hy3 vs Kimi K3", "url": "https://www.anchorterminal.com/compare/hy3-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-kimi-k3-1-pro.json", "title": "Hy3 vs Kimi K3.1 Pro", "url": "https://www.anchorterminal.com/compare/hy3-vs-kimi-k3-1-pro" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-kolibri-1.json", "title": "Hy3 vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/hy3-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-kronos.json", "title": "Hy3 vs Kronos", "url": "https://www.anchorterminal.com/compare/hy3-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-laguna-m-1.json", "title": "Hy3 vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/hy3-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-laguna-s-2-1.json", "title": "Hy3 vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/hy3-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-laguna-xs-2-1.json", "title": "Hy3 vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/hy3-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-lbs-27b.json", "title": "Hy3 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-lfm2-5-2-6b.json", "title": "Hy3 vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-audio-2b.json", "title": "Hy3 vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-omni-2b.json", "title": "Hy3 vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-vl-2b.json", "title": "Hy3 vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ling-3-0-tiny.json", "title": "Hy3 vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/hy3-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ling-3-1-flash-1019.json", "title": "Hy3 vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/hy3-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-longcat-2-5.json", "title": "Hy3 vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/hy3-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Hy3 vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/hy3-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-mimo-v2-6-flash-rl.json", "title": "Hy3 vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/hy3-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minicpm-o-4-5.json", "title": "Hy3 vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/hy3-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-1b.json", "title": "Hy3 vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-35b-a3b.json", "title": "Hy3 vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minicpm5-2b.json", "title": "Hy3 vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minimax-m2-5.json", "title": "Hy3 vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/hy3-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minimax-m2-7.json", "title": "Hy3 vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/hy3-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-minimax-m3-1-flash.json", "title": "Hy3 vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/hy3-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-mistral-large-4.json", "title": "Hy3 vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/hy3-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-muse-glimmer-30b.json", "title": "Hy3 vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/hy3-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-2-3b.json", "title": "Hy3 vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-3-33b.json", "title": "Hy3 vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Hy3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Hy3 vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-30b-a3b.json", "title": "Hy3 vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-4b.json", "title": "Hy3 vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Hy3 vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-super-120b-a12b.json", "title": "Hy3 vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-ultra-550b-a55b.json", "title": "Hy3 vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-north-mini-code-1-0.json", "title": "Hy3 vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/hy3-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-occamy-1-0.json", "title": "Hy3 vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/hy3-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-olmo-3-7b-think.json", "title": "Hy3 vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/hy3-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-122b.json", "title": "Hy3 vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-35b-a3b.json", "title": "Hy3 vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-397b.json", "title": "Hy3 vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-9b.json", "title": "Hy3 vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-otel-2-0-llm-31b-it.json", "title": "Hy3 vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/hy3-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen-agentworld-35b-a3b.json", "title": "Hy3 vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Hy3 vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-4b-instruct-2507.json", "title": "Hy3 vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-0-8b.json", "title": "Hy3 vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-122b-a10b.json", "title": "Hy3 vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-2b.json", "title": "Hy3 vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-397b-a17b.json", "title": "Hy3 vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-4b.json", "title": "Hy3 vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-9b.json", "title": "Hy3 vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-6-27b.json", "title": "Hy3 vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-6-35b-a3b.json", "title": "Hy3 vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-8-27b.json", "title": "Hy3 vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-8-flash-next.json", "title": "Hy3 vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Hy3 vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-coder-next.json", "title": "Hy3 vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Hy3 vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-2b-instruct.json", "title": "Hy3 vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Hy3 vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-32b-instruct.json", "title": "Hy3 vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-4b-instruct.json", "title": "Hy3 vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-8b-instruct.json", "title": "Hy3 vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-qwopus3-8-27b-flash-v2.json", "title": "Hy3 vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/hy3-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-recursive-flint.json", "title": "Hy3 vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/hy3-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview.json", "title": "Hy3 vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-sensenova-loop-9b-preview.json", "title": "Hy3 vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/hy3-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-smollm3-3b.json", "title": "Hy3 vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/hy3-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.json", "title": "Hy3 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-step-3-7-flash.json", "title": "Hy3 vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/hy3-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-swift-1-5-qwen3-8-27b.json", "title": "Hy3 vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/hy3-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Hy3 vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/hy3-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-thinkingcap-qwen3-8-27b.json", "title": "Hy3 vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/hy3-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-unlimited-ocr-2.json", "title": "Hy3 vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/hy3-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-wevisone-vl-2b.json", "title": "Hy3 vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/hy3-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-wevisone-vl-4b.json", "title": "Hy3 vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/hy3-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/hy3-vs-zaya1-8b.json", "title": "Hy3 vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/hy3-vs-zaya1-8b" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-lfm3-1-7b.json", "title": "Inkling-Small vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-1-7b.json", "title": "Inkling vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm3-1-7b.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-lfm3-1-7b.json", "title": "Kimi K3.1 Pro vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-1-7b.json", "title": "Kimi K3 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-lfm3-1-7b.json", "title": "Kolibri-1 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/kronos-vs-lfm3-1-7b.json", "title": "Kronos vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/kronos-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-lfm3-1-7b.json", "title": "Laguna M.1 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lfm3-1-7b.json", "title": "Laguna S 2.1 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lfm3-1-7b.json", "title": "Laguna XS 2.1 vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-lfm3-1-7b.json", "title": "LBS-27B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-1-7b.json", "title": "LFM2.5-2.6B vs LFM3-1.7B", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-1-7b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-audio-2b.json", "title": "LFM3-1.7B vs LFM3-Audio-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-audio-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-omni-2b.json", "title": "LFM3-1.7B vs LFM3-Omni-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-omni-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-vl-2b.json", "title": "LFM3-1.7B vs LFM3-VL-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ling-3-0-tiny.json", "title": "LFM3-1.7B vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ling-3-1-flash-1019.json", "title": "LFM3-1.7B vs Ling-3.1-flash-1019", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ling-3-1-flash-1019" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-longcat-2-5.json", "title": "LFM3-1.7B vs LongCat-2.5", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-longcat-2-5" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mimo-v2-6-distill-qwen-9b.json", "title": "LFM3-1.7B vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mimo-v2-6-flash-rl.json", "title": "LFM3-1.7B vs MiMo-V2.6-Flash-RL", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mimo-v2-6-flash-rl" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-o-4-5.json", "title": "LFM3-1.7B vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-v-4-7-1b.json", "title": "LFM3-1.7B vs MiniCPM-V 4.7 1B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-v-4-7-1b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-v-4-7-35b-a3b.json", "title": "LFM3-1.7B vs MiniCPM-V 4.7 35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-v-4-7-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm5-2b.json", "title": "LFM3-1.7B vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m2-5.json", "title": "LFM3-1.7B vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m2-7.json", "title": "LFM3-1.7B vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m3-1-flash.json", "title": "LFM3-1.7B vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mistral-large-4.json", "title": "LFM3-1.7B vs Mistral Large 4", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mistral-large-4" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-muse-glimmer-30b.json", "title": "LFM3-1.7B vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nanbeige-4-2-3b.json", "title": "LFM3-1.7B vs Nanbeige4.2-3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nanbeige-4-2-3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nanbeige-4-3-33b.json", "title": "LFM3-1.7B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "LFM3-1.7B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "LFM3-1.7B vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-30b-a3b.json", "title": "LFM3-1.7B vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-4b.json", "title": "LFM3-1.7B vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "LFM3-1.7B vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-super-120b-a12b.json", "title": "LFM3-1.7B vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-ultra-550b-a55b.json", "title": "LFM3-1.7B vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-north-mini-code-1-0.json", "title": "LFM3-1.7B vs North Mini Code 1.0", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-north-mini-code-1-0" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-occamy-1-0.json", "title": "LFM3-1.7B vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-olmo-3-7b-think.json", "title": "LFM3-1.7B vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-122b.json", "title": "LFM3-1.7B vs Ornith-1.5-122B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-122b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-35b-a3b.json", "title": "LFM3-1.7B vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-397b.json", "title": "LFM3-1.7B vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-9b.json", "title": "LFM3-1.7B vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-otel-2-0-llm-31b-it.json", "title": "LFM3-1.7B vs OTel-2.0-LLM-31B-IT", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-otel-2-0-llm-31b-it" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen-agentworld-35b-a3b.json", "title": "LFM3-1.7B vs Qwen-AgentWorld-35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen-agentworld-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-30b-a3b-instruct-2507.json", "title": "LFM3-1.7B vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-4b-instruct-2507.json", "title": "LFM3-1.7B vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-0-8b.json", "title": "LFM3-1.7B vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-122b-a10b.json", "title": "LFM3-1.7B vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-2b.json", "title": "LFM3-1.7B vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-397b-a17b.json", "title": "LFM3-1.7B vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-4b.json", "title": "LFM3-1.7B vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-9b.json", "title": "LFM3-1.7B vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-6-27b.json", "title": "LFM3-1.7B vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-6-35b-a3b.json", "title": "LFM3-1.7B vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-8-27b.json", "title": "LFM3-1.7B vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-8-flash-next.json", "title": "LFM3-1.7B vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-coder-30b-a3b-instruct.json", "title": "LFM3-1.7B vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-coder-next.json", "title": "LFM3-1.7B vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "LFM3-1.7B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-2b-instruct.json", "title": "LFM3-1.7B vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-30b-a3b-instruct.json", "title": "LFM3-1.7B vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-32b-instruct.json", "title": "LFM3-1.7B vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-4b-instruct.json", "title": "LFM3-1.7B vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-8b-instruct.json", "title": "LFM3-1.7B vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwopus3-8-27b-flash-v2.json", "title": "LFM3-1.7B vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-recursive-flint.json", "title": "LFM3-1.7B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ripple-65b-preview.json", "title": "LFM3-1.7B vs Ripple-65B Preview", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ripple-65b-preview" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-sensenova-loop-9b-preview.json", "title": "LFM3-1.7B vs SenseNova-Loop-9B-Preview", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-sensenova-loop-9b-preview" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-smollm3-3b.json", "title": "LFM3-1.7B vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-spark-x2-6-4b.json", "title": "LFM3-1.7B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-step-3-7-flash.json", "title": "LFM3-1.7B vs Step 3.7 Flash", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-step-3-7-flash" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-swift-1-5-qwen3-8-27b.json", "title": "LFM3-1.7B vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-swift-1-5-qwen3-8-flash-next.json", "title": "LFM3-1.7B vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-thinkingcap-qwen3-8-27b.json", "title": "LFM3-1.7B vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-unlimited-ocr-2.json", "title": "LFM3-1.7B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-wevisone-vl-2b.json", "title": "LFM3-1.7B vs WeVisOne-VL-2B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-wevisone-vl-2b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-wevisone-vl-4b.json", "title": "LFM3-1.7B vs WeVisOne-VL-4B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-wevisone-vl-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-zaya1-8b.json", "title": "LFM3-1.7B vs ZAYA1-8B", "url": "https://www.anchorterminal.com/compare/lfm3-1-7b-vs-zaya1-8b" } ], "panel": null, "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 15, "edge": "lfm3-1-7b", "hy3": 70, "key": "reach", "lfm3-1-7b": 85, "name": "Reach", "weight": 25 }, { "by": 20, "edge": "hy3", "hy3": 60, "key": "risk", "lfm3-1-7b": 40, "name": "Risk", "weight": 20 }, { "by": 25, "edge": "lfm3-1-7b", "hy3": 75, "key": "interface", "lfm3-1-7b": 100, "name": "Agent interface", "weight": 10 }, { "by": 11, "edge": "lfm3-1-7b", "hy3": 56, "key": "upkeep", "lfm3-1-7b": 67, "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Hy3 scores 62.6 (B) on agent readiness against LFM3-1.7B's 61 (C), and leads in 1 of 4 scored categories. LFM3-1.7B leads on reach, agent interface and documentation and upkeep. Both do open-weight models you run yourself.", "tasks": null, "tutorials": [], "verdicts": { "hy3": "Hy3 is a 295B mixture-of-experts model with 21B active, trained for several tool calls a turn, with per-request reasoning effort and 256K of context. It needs an 8-GPU server for FP8 or about 200 GB for a 4-bit build. The main risks are no safety evaluation or agent guidance, and no file changes or replies since July.", "lfm3-1-7b": "A 1.73B model that fits an 8 GB machine with room to spare, with a documented tool-call format, deferred tools, a thinking switch and a 256K context. It runs today in llama.cpp, Ollama and LM Studio only, loads in Transformers through repository code, and has no safety results, security contact or data sources." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b", "json": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b.min.md" }, "markdown": "Hy3 scores 62.6 (B) on agent readiness against LFM3-1.7B's 61 (C), and leads in 1 of 4 scored categories. LFM3-1.7B leads on reach, agent interface and documentation and upkeep. Both do open-weight models you run yourself.\n\n- Hy3: grade B, 62.6/100, rank #28 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/hy3.md · JSON https://www.anchorterminal.com/api/v1/tools/hy3.json\n- LFM3-1.7B: grade C, 61/100, rank #69 of 160 open-weight models. Markdown https://www.anchorterminal.com/tools/lfm3-1-7b.md · JSON https://www.anchorterminal.com/api/v1/tools/lfm3-1-7b.json\n- Best open-weight models you download and run yourself for AI agents: https://www.anchorterminal.com/best/open-weights/index.md\n- All 6359 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Hy3 (B)\n\nGood for: Teams with an 8-GPU server who want an agent-tuned MoE model under plain Apache 2.0\n\nAhead on:\n- Risk, 60 against 40\n\nWatch for: 597.6 GB in BF16, 299.9 GB in FP8 and 168.5 GB at the smallest 4-bit build\n\n### LFM3-1.7B (C)\n\nGood for: Agents on a laptop, phone or small server that need tool calling and a long context from a model under 2 GB at 4 bits\n\nAhead on:\n- Reach, 85 against 70\n- Agent interface, 100 against 75\n- Documentation and upkeep, 67 against 56\n\nWatch for: vLLM and SGLang have no released support, though the card lists both\n\n\n## Why the edge\n\n### Agent interface: LFM3-1.7B +25\n\n- Hy3 (75): The chat template earns 20, a chat_template.jinja in the repository. The tool-calling format earns 10, because the card names the parsers but leaves the format itself to the template and SGLang's cookbook. Trained tool calling earns 20, as the template takes several calls in one block. Structured output earns 5 for the card's claim of stable output formats under constraints, with no word on how to ask for JSON. Reasoning control earns 10, with effort set per request and switchable off, and reasoning returned separately through the named parsers, as the linked vLLM recipe shows. Context earns 10 for 262,144 tokens native.\n- LFM3-1.7B (100): Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, tools, deferred tools, tool results and the thinking switch. Tool-calling format 25, the card and Liquid's tool-use page document tools passed through `tools=` in apply_chat_template, calls returned as XML and results sent back as tool messages. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so several calls fit in one turn, and the card says the model was trained on tool calls and agentic traces and with reinforcement learning inside agent harnesses. Structured output 15, Liquid's API guide documents `response_format` with a JSON Schema, with lfm3-1.7b as the model in its examples, and says the schema is checked before generation starts. Reasoning control 10, the card documents `enable_thinking=False` in the chat template to turn reasoning off per request, with reasoning on by default inside think tags, and `preserve_thinking` for earlier turns. Context 10, 256K tokens per the card, which says the mid-training stage extended the context window to 256K, and max_position_embeddings 262144 in config.json. 20 + 25 + 20 + 15 + 10 + 10 = 100.\n\n### Risk: Hy3 +20\n\n- Hy3 (60): File safety earns the full 25, safetensors only with no pickle files, and the documented route runs vLLM or SGLang from their own code with a Jinja template, so nothing from the repository runs at load or prompt time. Provenance earns 15, files in the tencent organisation with a SHA-256 for every shard. Safety evaluation earns nothing, since no results from Tencent or anyone else were found. Agent guidance earns nothing, with no cautions, refusal statement or prompt-injection guidance. Licence risk keeps all 15 under plain Apache 2.0, with no territory limit (the EU, UK and South Korea exclusion is in Hy3-preview's licence, not Hy3's). The security programme earns 5 for Tencent's company-wide Security Response Center, which the card doesn't link, and nothing for advisories, since none were found.\n- LFM3-1.7B (40): File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, files in the LiquidAI organisation, which Liquid's docs page for the model and its blog post link to (10). Safety evaluation 0, no safety results on the card or in Liquid's blog post for the LFM3 family, neither of which mentions safety testing. Agent guidance 0, Nothing on prompt injection, an instruction hierarchy, what refusals cover or safeguards to add. Licence risk 10, 15 less 5 for the $10M annual revenue threshold on commercial use. Security programme 0, no way to report a flaw found. 15 + 15 + 0 + 0 + 10 + 0 = 40.\n\n### Reach: LFM3-1.7B +15\n\n- Hy3 (70): Memory earns 5, because the smallest build of 4-bit precision or better is AngelSlim's GPTQ-Int4 of 168.5 GB, about 202 GB with the fifth added, which is within 256 GB but beyond any single workstation. The 1-bit IQ1_M GGUF fits our reference machine but sits below the 4-bit line. Runtimes earn 20, for model code in released Transformers, vLLM, SGLang and llama.cpp; Ollama and LM Studio have no entry for it. Builds earn the full 15, with Tencent's FP8 repository and AngelSlim's GPTQ and GGUF builds. Terms earn 15 for plain Apache 2.0. Download earns 10, with no gate and no account. Hosted earns 5, since Featherless AI and DeepInfra serve it live through Hugging Face.\n- LFM3-1.7B (85): Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB, and 1.10 GB × 1.2 = 1.3 GB, which fits 8 GB, well inside the 16 GB line. Runtimes 15, Released llama.cpp has the lfm3 architecture (src/models/lfm3.cpp at b12242), Ollama's library has an lfm3 entry, and LM Studio's catalogue runs the architecture (its liquid/lfm3-vl-2b entry; lmstudio-community publishes a GGUF of this model). Builds 15, Liquid's GGUF repository holds Q4_0, Q4_K_M, Q8_0, F16 and BF16 files, and Liquid publishes 4-bit and 8-bit MLX builds and an ONNX repository, all in the LiquidAI organisation. Terms 10, the LFM Open License v1.0, a custom licence that lets anyone use it commercially for free below a threshold of $10M annual revenue. Download 10, the Hub API reports gated false for the model and its GGUF, MLX and ONNX repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Liquid's own API lists lfm3-1.7b among its models, so the publisher hosts it. 30 + 15 + 15 + 10 + 10 + 5 = 85.\n\n### Documentation and upkeep: LFM3-1.7B +11\n\n- Hy3 (56): The model card earns 11, covering intended use, architecture, parameters and context but not limitations, languages or a knowledge cut-off. Training data earns 5 for a general statement with no cut-off. The last change earns 10, a config.json edit on 20 July and AngelSlim uploads on 21 July, within 180 days on 2 November 2026; the line drops to 5 after 17 January 2027 unless the files change. Responsiveness earns 10, with Tencent replies on 7 of 19 discussions and none since 22 July. Version policy earns the full 10, since the preview stays in its own repository and the card dates it and says what changed. File health earns 10, with files that agree and no broken-file report waiting.\n- LFM3-1.7B (67): Model card 17, Intended use (local agents, tool calling, structured outputs, fine-tuning), a limitation (not recommended for agentic coding or complex multi-step reasoning), architecture (24 layers: 13 gated short convolutions, 5 sliding-window and 6 global attention), parameters (1.73B), context (256K) and 16 languages. Training data 5, A general description: 22T tokens of pre-training in two stages with the kinds of data added since LFM2, 1.75T tokens of supervised fine-tuning, then mixed reinforcement learning, distillation from six specialist teachers and agentic reinforcement learning. Last change 20, the last commit, on 9 November 2026, added the OpenVINO checkpoint to the card's inference table, a day before this check. Responsiveness 10, Of the 22 discussions that aren't pull requests (27 October to 8 November 2026), 7 have a reply from a LiquidAI member, which is some. Version policy 5, LFM3 came out in new repositories and the LFM2.5 models stay in theirs. File health 10, Config, template and card agree on the lfm3 architecture, the 262,144-token context and the thinking switch. 17 + 5 + 20 + 10 + 5 + 10 = 67.\n\n## Score by category\n\n| Category | Weight | Hy3 | LFM3-1.7B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 70 | 85 | LFM3-1.7B +15 |\n| Risk | 20% (20 this run) | 60 | 40 | Hy3 +20 |\n| Agent interface | 10% (10 this run) | 75 | 100 | LFM3-1.7B +25 |\n| Documentation and upkeep | 10% (10 this run) | 56 | 67 | LFM3-1.7B +11 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.6 · B** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Hy3 | LFM3-1.7B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Tencent (Hy team) | Liquid AI |\n| Hosted endpoint | no (local only) | no (local only) |\n| Transports | | |\n| Auth | None | None |\n| Pricing | Free | Free |\n| x402 | no | no |\n| Licence | Apache-2.0 | LFM Open License v1.0 (free commercial use below $10M annual revenue) |\n| Read-only variant documented | no | no |\n| llms.txt | no | yes |\n| Last release | 2026-07-20 | 2026-11-09 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Agent reviews | 2.8/5 (4) | none |\n\n## Verdicts\n\n**Hy3.** Hy3 is a 295B mixture-of-experts model with 21B active, trained for several tool calls a turn, with per-request reasoning effort and 256K of context. It needs an 8-GPU server for FP8 or about 200 GB for a 4-bit build. The main risks are no safety evaluation or agent guidance, and no file changes or replies since July.\n\n**LFM3-1.7B.** A 1.73B model that fits an 8 GB machine with room to spare, with a documented tool-call format, deferred tools, a thinking switch and a 256K context. It runs today in llama.cpp, Ollama and LM Studio only, loads in Transformers through repository code, and has no safety results, security contact or data sources.\n\n## Before you call either\n\n### Hy3\n\n1. Start it with vLLM on 8 GPUs, vllm serve tencent/Hy3-FP8 --tensor-parallel-size 8 --tool-call-parser hy_v3 --reasoning-parser hy_v3 --enable-auto-tool-choice --served-model-name hy3\n2. In SGLang use --tool-call-parser hunyuan --reasoning-parser hunyuan, as the card shows\n3. Pass reasoning_effort (no_think, low or high) in chat_template_kwargs; the default is no_think, and any other value raises a template error\n4. With the vLLM reasoning parser the chain of thought comes back in message.reasoning and the answer in message.content\n5. Earlier thinking stays in the prompt when tools are present; the template keys this on preserved_thinking, not the interleaved_thinking named in vLLM's recipe\n6. Use temperature 0.9 and top_p 1.0, the card's recommended sampling\n7. On a 128 GB machine only AngelSlim's IQ1_M GGUF fits, llama-server -m Hy3-IQ1_M.gguf -ctk q8_0 -ctv q8_0 -fa on -c 65536, with llama.cpp b11768 or later; at 89.4 GB × 1.2 it sits right at the 107.4 GB ceiling, so shorten the context if it fails to load, and expect a 1-bit build to fall short of Tencent's numbers\n8. Without the hardware, call it through Featherless AI or DeepInfra via Hugging Face's inference providers\n\n### LFM3-1.7B\n\n1. Start it with `llama-server -hf LiquidAI/LFM3-1.7B-GGUF:Q4_K_M --jinja` or `ollama run lfm3`\n2. Use temperature 0.1, top_k 50 and repetition penalty 1.1 for chat, tools and agents, per the card\n3. Pass `enable_thinking=False` for direct answers, and expect it to reason anyway on hard tasks\n4. For a large tool catalogue mark tools `defer_loading` and give it a search tool\n5. Don't plan on vLLM or SGLang until a release carries LFM3\n6. Liquid doesn't recommend it for agentic coding or complex multi-step reasoning\n\n## Questions\n\n### Which is better for AI agents, Hy3 or LFM3-1.7B?\n\nHy3 scores 62.6 (B) on agent readiness against LFM3-1.7B's 61 (C), and leads in 1 of 4 scored categories. LFM3-1.7B leads on reach, agent interface and documentation and upkeep.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hy3\", \"b\": \"lfm3-1-7b\"}`. From a terminal: `anchor compare hy3 lfm3-1-7b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hy3.json and https://www.anchorterminal.com/api/v1/tools/lfm3-1-7b.json\n\n## Other comparisons with Hy3 or LFM3-1.7B\n\n- [Agents-A1-4B vs Hy3](https://www.anchorterminal.com/compare/agents-a1-4b-vs-hy3.md)\n- [Agents-A1-4B vs LFM3-1.7B](https://www.anchorterminal.com/compare/agents-a1-4b-vs-lfm3-1-7b.md)\n- [Apertus v1.5 8B vs Hy3](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-hy3.md)\n- [Apertus v1.5 8B vs LFM3-1.7B](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lfm3-1-7b.md)\n- [Apodex-1.1-mini vs Hy3](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-hy3.md)\n- [Apodex-1.1-mini vs LFM3-1.7B](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lfm3-1-7b.md)\n- [Arete-27B vs Hy3](https://www.anchorterminal.com/compare/arete-27b-vs-hy3.md)\n- [Arete-27B vs LFM3-1.7B](https://www.anchorterminal.com/compare/arete-27b-vs-lfm3-1-7b.md)\n- [BigBang-v1 vs Hy3](https://www.anchorterminal.com/compare/bigbang-v1-vs-hy3.md)\n- [BigBang-v1 vs LFM3-1.7B](https://www.anchorterminal.com/compare/bigbang-v1-vs-lfm3-1-7b.md)\n- [Carbon-X vs Hy3](https://www.anchorterminal.com/compare/carbon-x-vs-hy3.md)\n- [Carbon-X vs LFM3-1.7B](https://www.anchorterminal.com/compare/carbon-x-vs-lfm3-1-7b.md)\n- [Cola2 vs Hy3](https://www.anchorterminal.com/compare/cola2-vs-hy3.md)\n- [Cola2 vs LFM3-1.7B](https://www.anchorterminal.com/compare/cola2-vs-lfm3-1-7b.md)\n- [Cosmos-Reason2-2B vs Hy3](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-hy3.md)\n- [Cosmos-Reason2-2B vs LFM3-1.7B](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lfm3-1-7b.md)\n- [Darwin-36B-Opus vs Hy3](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-hy3.md)\n- [Darwin-36B-Opus vs LFM3-1.7B](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lfm3-1-7b.md)\n- [DeepSeek-V3.2 vs Hy3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3.md)\n- [DeepSeek-V3.2 vs LFM3-1.7B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lfm3-1-7b.md)\n- [DeepSeek V4.1 Flash vs Hy3](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-hy3.md)\n- [DeepSeek V4.1 Flash vs LFM3-1.7B](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lfm3-1-7b.md)\n- [DeepSeek-V4-Flash-0731 vs Hy3](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-hy3.md)\n- [DeepSeek-V4-Flash-0731 vs LFM3-1.7B](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lfm3-1-7b.md)\n- [Devstral Small 2 vs Hy3](https://www.anchorterminal.com/compare/devstral-small-2-vs-hy3.md)\n- [Devstral Small 2 vs LFM3-1.7B](https://www.anchorterminal.com/compare/devstral-small-2-vs-lfm3-1-7b.md)\n- [DiffusionGemma 26B A4B IT vs Hy3](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-hy3.md)\n- [DiffusionGemma 26B A4B IT vs LFM3-1.7B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lfm3-1-7b.md)\n- [EXAONE 4.5 33B vs Hy3](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-hy3.md)\n- [EXAONE 4.5 33B vs LFM3-1.7B](https://www.anchorterminal.com/compare/exaone-4-5-33b-vs-lfm3-1-7b.md)\n- [Gemma 4 12B IT vs Hy3](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-hy3.md)\n- [Gemma 4 12B IT vs LFM3-1.7B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lfm3-1-7b.md)\n- [Gemma 4 26B A4B IT vs Hy3](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-hy3.md)\n- [Gemma 4 26B A4B IT vs LFM3-1.7B](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lfm3-1-7b.md)\n- [Gemma 4 31B IT vs Hy3](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-hy3.md)\n- [Gemma 4 31B IT vs LFM3-1.7B](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lfm3-1-7b.md)\n- [Gemma 4 E2B IT vs Hy3](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-hy3.md)\n- [Gemma 4 E2B IT vs LFM3-1.7B](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lfm3-1-7b.md)\n- [Gemma 4 E4B IT vs Hy3](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-hy3.md)\n- [Gemma 4 E4B IT vs LFM3-1.7B](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lfm3-1-7b.md)\n- [GLM-4.5-Air vs Hy3](https://www.anchorterminal.com/compare/glm-4-5-air-vs-hy3.md)\n- [GLM-4.5-Air vs LFM3-1.7B](https://www.anchorterminal.com/compare/glm-4-5-air-vs-lfm3-1-7b.md)\n- [GLM-4.7-Flash vs Hy3](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-hy3.md)\n- [GLM-4.7-Flash vs LFM3-1.7B](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lfm3-1-7b.md)\n- [GLM-5.3-Flash vs Hy3](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-hy3.md)\n- [GLM-5.3-Flash vs LFM3-1.7B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lfm3-1-7b.md)\n- [GLM-5.3 vs Hy3](https://www.anchorterminal.com/compare/glm-5-3-vs-hy3.md)\n- [GLM-5.3 vs LFM3-1.7B](https://www.anchorterminal.com/compare/glm-5-3-vs-lfm3-1-7b.md)\n- [gpt-oss-120b vs Hy3](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-hy3.md)\n- [gpt-oss-120b vs LFM3-1.7B](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lfm3-1-7b.md)\n- [gpt-oss-20b vs Hy3](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3.md)\n- [gpt-oss-20b vs LFM3-1.7B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lfm3-1-7b.md)\n- [Granite 4.2 30B vs Hy3](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-hy3.md)\n- [Granite 4.2 30B vs LFM3-1.7B](https://www.anchorterminal.com/compare/granite-4-2-30b-vs-lfm3-1-7b.md)\n- [Granite 4.2 3B vs Hy3](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-hy3.md)\n- [Granite 4.2 3B vs LFM3-1.7B](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lfm3-1-7b.md)\n- [Granite 4.2 8B vs Hy3](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-hy3.md)\n- [Granite 4.2 8B vs LFM3-1.7B](https://www.anchorterminal.com/compare/granite-4-2-8b-vs-lfm3-1-7b.md)\n- [Hy-Memory-30B-A3B vs Hy3](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-hy3.md)\n- [Hy-Memory-30B-A3B vs LFM3-1.7B](https://www.anchorterminal.com/compare/hy-memory-30b-a3b-vs-lfm3-1-7b.md)\n- [Hy3 vs Inkling](https://www.anchorterminal.com/compare/hy3-vs-inkling.md)\n- [Hy3 vs Inkling-Small](https://www.anchorterminal.com/compare/hy3-vs-inkling-small.md)\n- [Hy3 vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/hy3-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Hy3 vs Kimi K3](https://www.anchorterminal.com/compare/hy3-vs-kimi-k3.md)\n- [Hy3 vs Kimi K3.1 Pro](https://www.anchorterminal.com/compare/hy3-vs-kimi-k3-1-pro.md)\n- [Hy3 vs Kolibri-1](https://www.anchorterminal.com/compare/hy3-vs-kolibri-1.md)\n- [Hy3 vs Kronos](https://www.anchorterminal.com/compare/hy3-vs-kronos.md)\n- [Hy3 vs Laguna M.1](https://www.anchorterminal.com/compare/hy3-vs-laguna-m-1.md)\n- [Hy3 vs Laguna S 2.1](https://www.anchorterminal.com/compare/hy3-vs-laguna-s-2-1.md)\n- [Hy3 vs Laguna XS 2.1](https://www.anchorterminal.com/compare/hy3-vs-laguna-xs-2-1.md)\n- [Hy3 vs LBS-27B](https://www.anchorterminal.com/compare/hy3-vs-lbs-27b.md)\n- [Hy3 vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/hy3-vs-lfm2-5-2-6b.md)\n- [Hy3 vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/hy3-vs-lfm3-audio-2b.md)\n- [Hy3 vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/hy3-vs-lfm3-omni-2b.md)\n- [Hy3 vs LFM3-VL-2B](https://www.anchorterminal.com/compare/hy3-vs-lfm3-vl-2b.md)\n- [Hy3 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/hy3-vs-ling-3-0-tiny.md)\n- [Hy3 vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/hy3-vs-ling-3-1-flash-1019.md)\n- [Hy3 vs LongCat-2.5](https://www.anchorterminal.com/compare/hy3-vs-longcat-2-5.md)\n- [Hy3 vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/hy3-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Hy3 vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/hy3-vs-mimo-v2-6-flash-rl.md)\n- [Hy3 vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/hy3-vs-minicpm-o-4-5.md)\n- [Hy3 vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-1b.md)\n- [Hy3 vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/hy3-vs-minicpm-v-4-7-35b-a3b.md)\n- [Hy3 vs MiniCPM5-2B](https://www.anchorterminal.com/compare/hy3-vs-minicpm5-2b.md)\n- [Hy3 vs MiniMax-M2.5](https://www.anchorterminal.com/compare/hy3-vs-minimax-m2-5.md)\n- [Hy3 vs MiniMax-M2.7](https://www.anchorterminal.com/compare/hy3-vs-minimax-m2-7.md)\n- [Hy3 vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/hy3-vs-minimax-m3-1-flash.md)\n- [Hy3 vs Mistral Large 4](https://www.anchorterminal.com/compare/hy3-vs-mistral-large-4.md)\n- [Hy3 vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/hy3-vs-muse-glimmer-30b.md)\n- [Hy3 vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-2-3b.md)\n- [Hy3 vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/hy3-vs-nanbeige-4-3-33b.md)\n- [Hy3 vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Hy3 vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Hy3 vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-30b-a3b.md)\n- [Hy3 vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-4b.md)\n- [Hy3 vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Hy3 vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-super-120b-a12b.md)\n- [Hy3 vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/hy3-vs-nemotron-3-ultra-550b-a55b.md)\n- [Hy3 vs North Mini Code 1.0](https://www.anchorterminal.com/compare/hy3-vs-north-mini-code-1-0.md)\n- [Hy3 vs occamy-1.0](https://www.anchorterminal.com/compare/hy3-vs-occamy-1-0.md)\n- [Hy3 vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/hy3-vs-olmo-3-7b-think.md)\n- [Hy3 vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-122b.md)\n- [Hy3 vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-35b-a3b.md)\n- [Hy3 vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-397b.md)\n- [Hy3 vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/hy3-vs-ornith-1-5-9b.md)\n- [Hy3 vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/hy3-vs-otel-2-0-llm-31b-it.md)\n- [Hy3 vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/hy3-vs-qwen-agentworld-35b-a3b.md)\n- [Hy3 vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/hy3-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Hy3 vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/hy3-vs-qwen3-4b-instruct-2507.md)\n- [Hy3 vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-0-8b.md)\n- [Hy3 vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-122b-a10b.md)\n- [Hy3 vs Qwen3.5-2B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-2b.md)\n- [Hy3 vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-397b-a17b.md)\n- [Hy3 vs Qwen3.5-4B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-4b.md)\n- [Hy3 vs Qwen3.5-9B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-5-9b.md)\n- [Hy3 vs Qwen3.6-27B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-6-27b.md)\n- [Hy3 vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-6-35b-a3b.md)\n- [Hy3 vs Qwen3.8-27B](https://www.anchorterminal.com/compare/hy3-vs-qwen3-8-27b.md)\n- [Hy3 vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/hy3-vs-qwen3-8-flash-next.md)\n- [Hy3 vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Hy3 vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/hy3-vs-qwen3-coder-next.md)\n- [Hy3 vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Hy3 vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-2b-instruct.md)\n- [Hy3 vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Hy3 vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-32b-instruct.md)\n- [Hy3 vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-4b-instruct.md)\n- [Hy3 vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/hy3-vs-qwen3-vl-8b-instruct.md)\n- [Hy3 vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/hy3-vs-qwopus3-8-27b-flash-v2.md)\n- [Hy3 vs Recursive Flint](https://www.anchorterminal.com/compare/hy3-vs-recursive-flint.md)\n- [Hy3 vs Ripple-65B Preview](https://www.anchorterminal.com/compare/hy3-vs-ripple-65b-preview.md)\n- [Hy3 vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/hy3-vs-sensenova-loop-9b-preview.md)\n- [Hy3 vs SmolLM3-3B](https://www.anchorterminal.com/compare/hy3-vs-smollm3-3b.md)\n- [Hy3 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.md)\n- [Hy3 vs Step 3.7 Flash](https://www.anchorterminal.com/compare/hy3-vs-step-3-7-flash.md)\n- [Hy3 vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/hy3-vs-swift-1-5-qwen3-8-27b.md)\n- [Hy3 vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/hy3-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Hy3 vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/hy3-vs-thinkingcap-qwen3-8-27b.md)\n- [Hy3 vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/hy3-vs-unlimited-ocr-2.md)\n- [Hy3 vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/hy3-vs-wevisone-vl-2b.md)\n- [Hy3 vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/hy3-vs-wevisone-vl-4b.md)\n- [Hy3 vs ZAYA1-8B](https://www.anchorterminal.com/compare/hy3-vs-zaya1-8b.md)\n- [Inkling-Small vs LFM3-1.7B](https://www.anchorterminal.com/compare/inkling-small-vs-lfm3-1-7b.md)\n- [Inkling vs LFM3-1.7B](https://www.anchorterminal.com/compare/inkling-vs-lfm3-1-7b.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM3-1.7B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lfm3-1-7b.md)\n- [Kimi K3.1 Pro vs LFM3-1.7B](https://www.anchorterminal.com/compare/kimi-k3-1-pro-vs-lfm3-1-7b.md)\n- [Kimi K3 vs LFM3-1.7B](https://www.anchorterminal.com/compare/kimi-k3-vs-lfm3-1-7b.md)\n- [Kolibri-1 vs LFM3-1.7B](https://www.anchorterminal.com/compare/kolibri-1-vs-lfm3-1-7b.md)\n- [Kronos vs LFM3-1.7B](https://www.anchorterminal.com/compare/kronos-vs-lfm3-1-7b.md)\n- [Laguna M.1 vs LFM3-1.7B](https://www.anchorterminal.com/compare/laguna-m-1-vs-lfm3-1-7b.md)\n- [Laguna S 2.1 vs LFM3-1.7B](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lfm3-1-7b.md)\n- [Laguna XS 2.1 vs LFM3-1.7B](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lfm3-1-7b.md)\n- [LBS-27B vs LFM3-1.7B](https://www.anchorterminal.com/compare/lbs-27b-vs-lfm3-1-7b.md)\n- [LFM2.5-2.6B vs LFM3-1.7B](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-lfm3-1-7b.md)\n- [LFM3-1.7B vs LFM3-Audio-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-audio-2b.md)\n- [LFM3-1.7B vs LFM3-Omni-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-omni-2b.md)\n- [LFM3-1.7B vs LFM3-VL-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-lfm3-vl-2b.md)\n- [LFM3-1.7B vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ling-3-0-tiny.md)\n- [LFM3-1.7B vs Ling-3.1-flash-1019](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ling-3-1-flash-1019.md)\n- [LFM3-1.7B vs LongCat-2.5](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-longcat-2-5.md)\n- [LFM3-1.7B vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mimo-v2-6-distill-qwen-9b.md)\n- [LFM3-1.7B vs MiMo-V2.6-Flash-RL](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mimo-v2-6-flash-rl.md)\n- [LFM3-1.7B vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-o-4-5.md)\n- [LFM3-1.7B vs MiniCPM-V 4.7 1B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-v-4-7-1b.md)\n- [LFM3-1.7B vs MiniCPM-V 4.7 35B-A3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm-v-4-7-35b-a3b.md)\n- [LFM3-1.7B vs MiniCPM5-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minicpm5-2b.md)\n- [LFM3-1.7B vs MiniMax-M2.5](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m2-5.md)\n- [LFM3-1.7B vs MiniMax-M2.7](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m2-7.md)\n- [LFM3-1.7B vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-minimax-m3-1-flash.md)\n- [LFM3-1.7B vs Mistral Large 4](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-mistral-large-4.md)\n- [LFM3-1.7B vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-muse-glimmer-30b.md)\n- [LFM3-1.7B vs Nanbeige4.2-3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nanbeige-4-2-3b.md)\n- [LFM3-1.7B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nanbeige-4-3-33b.md)\n- [LFM3-1.7B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [LFM3-1.7B vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [LFM3-1.7B vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-30b-a3b.md)\n- [LFM3-1.7B vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-4b.md)\n- [LFM3-1.7B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [LFM3-1.7B vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-super-120b-a12b.md)\n- [LFM3-1.7B vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-nemotron-3-ultra-550b-a55b.md)\n- [LFM3-1.7B vs North Mini Code 1.0](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-north-mini-code-1-0.md)\n- [LFM3-1.7B vs occamy-1.0](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-occamy-1-0.md)\n- [LFM3-1.7B vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-olmo-3-7b-think.md)\n- [LFM3-1.7B vs Ornith-1.5-122B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-122b.md)\n- [LFM3-1.7B vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-35b-a3b.md)\n- [LFM3-1.7B vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-397b.md)\n- [LFM3-1.7B vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ornith-1-5-9b.md)\n- [LFM3-1.7B vs OTel-2.0-LLM-31B-IT](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-otel-2-0-llm-31b-it.md)\n- [LFM3-1.7B vs Qwen-AgentWorld-35B-A3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen-agentworld-35b-a3b.md)\n- [LFM3-1.7B vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-30b-a3b-instruct-2507.md)\n- [LFM3-1.7B vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-4b-instruct-2507.md)\n- [LFM3-1.7B vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-0-8b.md)\n- [LFM3-1.7B vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-122b-a10b.md)\n- [LFM3-1.7B vs Qwen3.5-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-2b.md)\n- [LFM3-1.7B vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-397b-a17b.md)\n- [LFM3-1.7B vs Qwen3.5-4B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-4b.md)\n- [LFM3-1.7B vs Qwen3.5-9B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-5-9b.md)\n- [LFM3-1.7B vs Qwen3.6-27B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-6-27b.md)\n- [LFM3-1.7B vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-6-35b-a3b.md)\n- [LFM3-1.7B vs Qwen3.8-27B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-8-27b.md)\n- [LFM3-1.7B vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-8-flash-next.md)\n- [LFM3-1.7B vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-coder-30b-a3b-instruct.md)\n- [LFM3-1.7B vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-coder-next.md)\n- [LFM3-1.7B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [LFM3-1.7B vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-2b-instruct.md)\n- [LFM3-1.7B vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-30b-a3b-instruct.md)\n- [LFM3-1.7B vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-32b-instruct.md)\n- [LFM3-1.7B vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-4b-instruct.md)\n- [LFM3-1.7B vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwen3-vl-8b-instruct.md)\n- [LFM3-1.7B vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-qwopus3-8-27b-flash-v2.md)\n- [LFM3-1.7B vs Recursive Flint](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-recursive-flint.md)\n- [LFM3-1.7B vs Ripple-65B Preview](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-ripple-65b-preview.md)\n- [LFM3-1.7B vs SenseNova-Loop-9B-Preview](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-sensenova-loop-9b-preview.md)\n- [LFM3-1.7B vs SmolLM3-3B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-smollm3-3b.md)\n- [LFM3-1.7B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-spark-x2-6-4b.md)\n- [LFM3-1.7B vs Step 3.7 Flash](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-step-3-7-flash.md)\n- [LFM3-1.7B vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-swift-1-5-qwen3-8-27b.md)\n- [LFM3-1.7B vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-swift-1-5-qwen3-8-flash-next.md)\n- [LFM3-1.7B vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-thinkingcap-qwen3-8-27b.md)\n- [LFM3-1.7B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-unlimited-ocr-2.md)\n- [LFM3-1.7B vs WeVisOne-VL-2B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-wevisone-vl-2b.md)\n- [LFM3-1.7B vs WeVisOne-VL-4B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-wevisone-vl-4b.md)\n- [LFM3-1.7B vs ZAYA1-8B](https://www.anchorterminal.com/compare/lfm3-1-7b-vs-zaya1-8b.md)\n", "meta": { "attribution": "Anchor Terminal (https://www.anchorterminal.com)", "attributionRequired": true, "credit": "CC BY 4.0, credit Anchor Terminal and link the page or API address you took it from (https://www.anchorterminal.com/terms/#data)", "docs": "https://www.anchorterminal.com/docs/", "generatedAt": "2026-11-11", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.7", "openapi": "https://www.anchorterminal.com/openapi.json", "preview": false, "run": "2026-10-01", "runLabel": "October 2026 research run", "terms": "https://www.anchorterminal.com/terms/#data" }, "page": { "breadcrumbs": [ { "name": "Home", "url": "https://www.anchorterminal.com/" }, { "name": "Compare", "url": "https://www.anchorterminal.com/compare/" }, { "name": "Hy3 vs LFM3-1.7B", "url": "" } ], "description": "Hy3 scores 62.6 (B) to LFM3-1.7B's 61 (C) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Hy3 B 62.6", "LFM3-1.7B C 61", "scores" ], "h1": "Hy3 vs LFM3-1.7B", "image": "https://www.anchorterminal.com/assets/og/default.png", "path": "/compare/hy3-vs-lfm3-1-7b", "published": "2026-10-01", "section": "tools", "title": "Hy3 vs LFM3-1.7B for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-11-10", "url": "https://www.anchorterminal.com/compare/hy3-vs-lfm3-1-7b" }, "tokens": { "markdown": 9000, "slim": 780 }, "version": 1 }