{ "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", "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": "2026-10-21" }, "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": 1197, "categoryRank": 22, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 57, "interface": 75, "reach": 70, "risk": 60, "upkeep": 56 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-21" }, "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": "0.6", "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": 60, "checked": { "categories": { "capability": "2026-10-21", "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "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" ], "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": 60 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/hy3.json" }, "answer": "Hy3 scores 62.6 (B) on agent readiness against Spark-X2.6-4B's 61 (C), and leads in 3 of 4 scored categories. Spark-X2.6-4B leads on reach.", "b": { "slug": "spark-x2-6-4b", "name": "Spark-X2.6-4B", "vendor": "SparkLLM (XHToken)", "vendorUrl": "https://huggingface.co/XHToken", "kind": "weights", "category": "open-weights", "summary": "Spark-X2.6-4B is SparkLLM's open-weight 4B text model, Spark-X2.5-4B's architecture with new post-training, a 1M-token context and three thinking levels, on Hugging Face with FP8, INT8, INT4 and GGUF builds under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/spark-x2-6-4b", "markdownUrl": "https://www.anchorterminal.com/tools/spark-x2-6-4b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/spark-x2-6-4b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/spark-x2-6-4b.json", "repo": "https://huggingface.co/XHToken/Spark-X2.6-4B", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "XHToken/Spark-X2.6-4B" }, { "registry": "huggingface", "name": "XHToken/Spark-X2.6-4B-GGUF" }, { "registry": "huggingface", "name": "XHToken/Spark-X2.6-4B-FP8" }, { "registry": "huggingface", "name": "XHToken/Spark-X2.6-4B-INT8" }, { "registry": "huggingface", "name": "XHToken/Spark-X2.6-4B-INT4" }, { "registry": "ollama", "name": "SparkLLM/Spark-X2.6-4B" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. None of the six X2.6 repositories is gated (checked 2026-10-21).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0. Nothing is hosted by SparkLLM or by an inference provider listed on Hugging Face. Running it yourself costs the hardware, 8.24 GB for the BF16 files and 3.19 GB for SparkLLM's Q4_K_M GGUF (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": "2026-10-21" }, "docsUrl": "https://huggingface.co/XHToken/Spark-X2.6-4B", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "small", "long-context", "reasoning", "tool-calling", "apache-2.0", "safetensors", "gguf", "fp8", "self-hosted" ], "lastRelease": "2026-10-20", "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": 1197, "categoryRank": 41, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 70, "reach": 85, "risk": 50, "upkeep": 41 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-21" }, "negative": 0, "verdict": "A tiny cousin for coding and tool-calling loops with a 1M-token context and thinking that is off, low or high, which runs in about 4 GB from SparkLLM's 4-bit GGUF. Use llama.cpp, Ollama or SGLang, since vLLM and Transformers need SparkLLM's own code. The risks are no safety work or agent guidance and a thin, two-day-old card.", "bestFor": "Agents that want a tiny local model for tool loops and long documents on a laptop, CPU or small GPU.", "strengths": [ "SparkLLM's Q4_K_M GGUF fits in about 4 GB, and FP8, INT8, INT4 and Q8_0 builds come from the publisher", "Plain Apache 2.0 on its own base, with no gate or account", "1,048,576 tokens of context with sliding-window layers that keep the cache small", "Released support in llama.cpp, SGLang and Ollama, with SGLang's own spark25 tool parser", "Thinking that turns off per request or runs at low or high effort, and several tool calls a turn", "A private security reporting route in SparkLLM's GitHub" ], "weaknesses": [ "No safety results and no agent or prompt-injection guidance", "Transformers and vLLM need code from SparkLLM's repositories", "Tool format and structured output aren't documented, and the template uses its own arg_key format", "The card has no limitations, cut-off, architecture description or training data, and leans on X2.5's", "Released on 19 and 20 October 2026, with no downloads, discussions or independent results yet" ], "agentNotes": [ "Quickest start is `llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q4_K_M --jinja`, which needs llama.cpp b10828 or later, or `ollama run SparkLLM/Spark-X2.6-4B` (8.2 GB, Ollama 0.34.1 or later)", "For parsed tool calls serve it with SGLang 0.5.22 or later, `--tool-call-parser spark25 --reasoning-parser qwen3`, since the calls come back as tool_call blocks with arg_key and arg_value pairs", "Thinking is on by default. Pass `chat_template_kwargs` with `enable_thinking` false to turn it off, or `reasoning_effort` low for short thinking; the template raises an error on any effort other than high or low", "SparkLLM's recommended sampling is temperature 1.0, top_p 0.95 and top_k -1", "The template always opens with its own default system line, with the effort instruction, and puts your system message after the tool list", "The template raises an error if tool_call arguments are a JSON string, so pass them as an object", "Set the context yourself, the card's 1,048,576-token example needs far more memory than the weights" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "C", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 61 } ], "editorialScores": { "interface": 70, "reach": 85, "risk": 50, "upkeep": 41 }, "provenanceScore": 40, "checked": { "categories": { "interface": "2026-10-21", "reach": "2026-10-21", "risk": "2026-10-21", "upkeep": "2026-10-21" }, "last": "2026-10-21", "oldest": "2026-10-21", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q8_0 --jinja -c 131072\n# or, with SGLang 0.5.22 or later:\npython -m sglang.launch_server --model-path XHToken/Spark-X2.6-4B \\\n --tool-call-parser spark25 --reasoning-parser qwen3 --context-length 131072", "http": "curl http://localhost:30000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\"model\": \"XHToken/Spark-X2.6-4B\", \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}], \"temperature\": 1.0, \"top_p\": 0.95}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/spark-x2-6-4b" }, "weights": { "trainedBy": "SparkLLM (XHToken)", "builtOn": "XHToken/Spark-X2.6-4B-Base (SparkLLM's own checkpoint, Apache 2.0, declared as the base in the card's metadata). The card's text says X2.6 builds on Spark-X2.5-4B with improved post-training. The Base repository's card is a cut-down copy of this card that calls its files the post-trained model", "params": "4.11B", "context": 1048576, "goodFor": "Small dense text model for coding, tool use and agent loops on a laptop or small GPU, with a 1M-token context and thinking that is off, low or high per request.", "runtimes": [ "llama.cpp", "Ollama", "SGLang" ], "builds": [ { "name": "Spark-X2.6-4B-FP8", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-FP8", "who": "publisher", "precision": "fp8", "sizeGB": 4.47, "memoryGB": 8, "format": "safetensors", "note": "compressed-tensors float-quantized" }, { "name": "Spark-X2.6-4B-INT8", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-INT8", "who": "publisher", "precision": "int8", "sizeGB": 4.47, "memoryGB": 8, "format": "safetensors", "note": "compressed-tensors int-quantized, 8-bit weights and activations" }, { "name": "Spark-X2.6-4B-INT4", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-INT4", "who": "publisher", "precision": "int4", "sizeGB": 3.43, "memoryGB": 8, "format": "safetensors", "note": "compressed-tensors pack-quantized, 4-bit weights in groups of 32 on the attention and MLP projections, the rest in BF16" }, { "name": "Spark-X2.6-4B-Q4_K_M.gguf", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/blob/main/Spark-X2.6-4B-Q4_K_M.gguf", "who": "publisher", "precision": "q4_k_m", "sizeGB": 3.19, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp", "Ollama" ], "note": "The smallest build at 4-bit or better. 0.59 GB larger than X2.5's Q4_K_M" }, { "name": "Spark-X2.6-4B-Q8_0.gguf", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/blob/main/Spark-X2.6-4B-Q8_0.gguf", "who": "publisher", "precision": "q8_0", "sizeGB": 4.38, "memoryGB": 8, "format": "gguf", "runsOn": [ "llama.cpp", "Ollama" ] }, { "name": "Spark-X2.6-4B", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B", "who": "publisher", "precision": "bf16", "sizeGB": 8.24, "memoryGB": 12, "format": "safetensors", "runsOn": [ "SGLang" ], "note": "Transformers loads it only with trust_remote_code (modeling_spark.py), and vLLM only with SparkLLM's out-of-tree plugin" }, { "name": "Spark-X2.6-4B.gguf", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-GGUF/blob/main/Spark-X2.6-4B.gguf", "who": "publisher", "precision": "bf16", "sizeGB": 8.23, "memoryGB": 12, "format": "gguf" }, { "name": "ollama SparkLLM/Spark-X2.6-4B:latest", "url": "https://ollama.com/SparkLLM/Spark-X2.6-4B", "who": "publisher", "precision": "bf16", "sizeGB": 8.2, "memoryGB": 12, "format": "ollama", "runsOn": [ "Ollama" ], "note": "SparkLLM's own namespace on Ollama, not Ollama's library. The only tag is 8.2 GB (digest 44ca4d700630), so it is the unquantised build; needs Ollama 0.34.1 or later. Size as Ollama shows it" } ], "run": "llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q8_0 --jinja -c 131072", "runBuild": "Spark-X2.6-4B-Q8_0.gguf", "checked": "2026-10-21", "minMemoryGB": 8 }, "family": { "lab": "SparkLLM (XHToken)", "family": "Spark-X2 (X2.5, X2.6)", "url": "https://www.anchorterminal.com/open-weights/#sparkllm", "others": [ { "name": "Spark-X2.6-4B-Base", "url": "https://huggingface.co/XHToken/Spark-X2.6-4B-Base", "params": "4B (Hub safetensors count 4.11B)" }, { "name": "Spark-X2.5-4B-Base", "url": "https://huggingface.co/XHToken/Spark-X2.5-4B-Base", "params": "4B (Hub safetensors count 4.11B)" }, { "name": "Spark-X2.5-1.7B-Base", "url": "https://huggingface.co/XHToken/Spark-X2.5-1.7B-Base", "params": "1.7B (Hub safetensors count 1.71B)" }, { "name": "Spark-X2.5-4B", "url": "https://huggingface.co/XHToken/Spark-X2.5-4B", "params": "4B (Hub safetensors count 4.11B)" }, { "name": "Spark-X2.5-1.7B", "url": "https://huggingface.co/XHToken/Spark-X2.5-1.7B", "params": "1.7B (Hub safetensors count 1.71B)" } ] }, "area": "models", "provenance": { "legalEntity": "XHToken (the licence's copyright line); the Hugging Face organisation's name is SparkLLM", "domain": "", "domainRegistered": "", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "", "securityTxt": "none", "checked": "2026-10-21", "notes": [ "The Hugging Face organisation XHToken (fullname SparkLLM, 18 members) isn't verified. No company website was found on the card or the organisation page; the card links Slack, Discord, YouTube, dev.to, Bluesky, X, Zhihu and WeChat, and SparkLLM's GitHub repositories.", "SparkLLM's GitHub organisation XHToken documents its Hugging Face repositories by name (Spark-MLX-LLM's README), and the X2.6 card points to Spark-plugin, Spark-MLX-LLM and XHToken/LlamaFactory there, which ties the two together.", "XHToken/community on GitHub has a SECURITY.md with a private advisory route and a security email, which Spark-plugin's SECURITY.md points to.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "No changelog. The commits from 19 and 20 October 2026 are uploads titled only \"Upload Spark-X2.6-4B model files\"." ], "score": 40 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/spark-x2-6-4b.json" }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Tencent (Hy team)", "b": "SparkLLM (XHToken)", "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": "Apache-2.0", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-07-20", "b": "2026-10-20", "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": "", "b": "", "name": "Customer content may train models" }, { "a": "", "b": "", "name": "Terms restrict automated access" }, { "a": "", "b": "", "name": "Terms restrict benchmarking" }, { "a": "", "b": "", "name": "Terms or service can change without notice" }, { "a": "", "b": "", "name": "Arbitration or class-action waiver" }, { "a": "2.8/5 (4)", "b": "3/5 (4)", "name": "Agent reviews" } ], "faq": [ { "answer": "Hy3 scores 62.6 (B) on agent readiness against Spark-X2.6-4B's 61 (C), and leads in 3 of 4 scored categories. Spark-X2.6-4B leads on reach.", "question": "Which is better for AI agents, Hy3 or Spark-X2.6-4B?" } ], "goodFor": [ { "aheadOn": [ "Risk, 60 against 50", "Agent interface, 75 against 70", "Documentation and upkeep, 56 against 41" ], "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" ], "also": null, "goodFor": "Agents that want a tiny local model for tool loops and long documents on a laptop, CPU or small GPU.", "slug": "spark-x2-6-4b", "watchFor": "No safety results and no agent or prompt-injection guidance" } ], "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-spark-x2-6-4b.json", "title": "Agents-A1-4B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Apertus v1.5 8B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Apodex-1.1-mini vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "BigBang-v1 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Cosmos-Reason2-2B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Darwin-36B-Opus vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "DeepSeek-V3.2 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "DeepSeek V4.1 Flash vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "DeepSeek-V4-Flash-0731 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "DiffusionGemma 26B A4B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Gemma 4 12B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Gemma 4 26B A4B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Gemma 4 31B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Gemma 4 E2B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Gemma 4 E4B IT vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "GLM-4.5-Air vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "GLM-4.7-Flash vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "GLM-5.3-Flash vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "GLM-5.3 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "gpt-oss-120b vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "gpt-oss-20b vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-spark-x2-6-4b" }, { "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-spark-x2-6-4b.json", "title": "Granite 4.2 3B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-spark-x2-6-4b" }, { "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-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-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-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-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-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-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-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-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-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-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-1-5-35b-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-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-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-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/inkling-small-vs-spark-x2-6-4b.json", "title": "Inkling-Small vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b.json", "title": "Inkling vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-spark-x2-6-4b.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-spark-x2-6-4b.json", "title": "Kimi K3 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-spark-x2-6-4b.json", "title": "Kolibri-1 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-spark-x2-6-4b.json", "title": "Laguna M.1 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-spark-x2-6-4b.json", "title": "Laguna S 2.1 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-spark-x2-6-4b.json", "title": "Laguna XS 2.1 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-spark-x2-6-4b.json", "title": "LFM2.5-2.6B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-spark-x2-6-4b.json", "title": "Ling-3.0-tiny vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-spark-x2-6-4b.json", "title": "MiMo-V2.6 Distill Qwen 9B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-spark-x2-6-4b.json", "title": "MiniCPM-o 4.5 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-spark-x2-6-4b.json", "title": "MiniCPM5-2B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/minicpm5-2b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-spark-x2-6-4b.json", "title": "MiniMax-M2.5 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/minimax-m2-5-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-spark-x2-6-4b.json", "title": "MiniMax-M2.7 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/minimax-m2-7-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-spark-x2-6-4b.json", "title": "Muse Glimmer 30B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-spark-x2-6-4b.json", "title": "Nemotron 3.5 Lightning 30B A3B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-spark-x2-6-4b.json", "title": "Nemotron 3 Nano 30B A3B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-spark-x2-6-4b.json", "title": "Nemotron 3 Nano 4B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-spark-x2-6-4b.json", "title": "Nemotron 3 Nano Omni 30B A3B Reasoning vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-spark-x2-6-4b.json", "title": "Nemotron 3 Super 120B A12B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-spark-x2-6-4b.json", "title": "Nemotron 3 Ultra 550B A55B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/occamy-1-0-vs-spark-x2-6-4b.json", "title": "occamy-1.0 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/occamy-1-0-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-spark-x2-6-4b.json", "title": "Olmo 3 7B Think vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-spark-x2-6-4b.json", "title": "Ornith-1.5-35B-A3B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-spark-x2-6-4b.json", "title": "Ornith-1.5-397B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-spark-x2-6-4b.json", "title": "Ornith-1.5-9B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-spark-x2-6-4b.json", "title": "Qwen3-30B-A3B-Instruct-2507 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-spark-x2-6-4b.json", "title": "Qwen3-4B-Instruct-2507 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-spark-x2-6-4b.json", "title": "Qwen3.5-0.8B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-spark-x2-6-4b.json", "title": "Qwen3.5-122B-A10B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-spark-x2-6-4b.json", "title": "Qwen3.5-2B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-5-2b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-spark-x2-6-4b.json", "title": "Qwen3.5-397B-A17B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-spark-x2-6-4b.json", "title": "Qwen3.5-4B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-5-4b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-spark-x2-6-4b.json", "title": "Qwen3.5-9B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-5-9b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-spark-x2-6-4b.json", "title": "Qwen3.6-27B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-6-27b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-spark-x2-6-4b.json", "title": "Qwen3.6-35B-A3B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-spark-x2-6-4b.json", "title": "Qwen3.8-27B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-8-27b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-spark-x2-6-4b.json", "title": "Qwen3.8-Flash-Next vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-Coder-30B-A3B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-spark-x2-6-4b.json", "title": "Qwen3-Coder-Next vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-coder-next-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-Omni-30B-A3B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-VL-2B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-VL-30B-A3B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-VL-32B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-VL-4B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-spark-x2-6-4b.json", "title": "Qwen3-VL-8B-Instruct vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-spark-x2-6-4b.json", "title": "Qwopus3.8-27B-Flash-V2 vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/smollm3-3b-vs-spark-x2-6-4b.json", "title": "SmolLM3-3B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/smollm3-3b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-swift-1-5-qwen3-8-27b.json", "title": "Spark-X2.6-4B vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Spark-X2.6-4B vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-thinkingcap-qwen3-8-27b.json", "title": "Spark-X2.6-4B vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-thinkingcap-qwen3-8-27b" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 15, "edge": "spark-x2-6-4b", "hy3": 70, "key": "reach", "name": "Reach", "spark-x2-6-4b": 85, "weight": 25 }, { "by": 10, "edge": "hy3", "hy3": 60, "key": "risk", "name": "Risk", "spark-x2-6-4b": 50, "weight": 20 }, { "by": 5, "edge": "hy3", "hy3": 75, "key": "interface", "name": "Agent interface", "spark-x2-6-4b": 70, "weight": 10 }, { "by": 15, "edge": "hy3", "hy3": 56, "key": "upkeep", "name": "Documentation and upkeep", "spark-x2-6-4b": 41, "weight": 10 } ], "summary": "Hy3 scores 62.6 (B) on agent readiness against Spark-X2.6-4B's 61 (C), and leads in 3 of 4 scored categories. Spark-X2.6-4B leads on reach. Both do open-weight models you run yourself.", "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.", "spark-x2-6-4b": "A tiny cousin for coding and tool-calling loops with a 1M-token context and thinking that is off, low or high, which runs in about 4 GB from SparkLLM's 4-bit GGUF. Use llama.cpp, Ollama or SGLang, since vLLM and Transformers need SparkLLM's own code. The risks are no safety work or agent guidance and a thin, two-day-old card." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b", "json": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.min.md" }, "markdown": "Hy3 scores 62.6 (B) on agent readiness against Spark-X2.6-4B's 61 (C), and leads in 3 of 4 scored categories. Spark-X2.6-4B leads on reach. Both do open-weight models you run yourself.\n\n- Hy3: grade B, 62.6/100, rank #27 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/hy3.md · JSON https://www.anchorterminal.com/api/v1/tools/hy3.json\n- Spark-X2.6-4B: grade C, 61/100, rank #48 of 100 open-weight models. Markdown https://www.anchorterminal.com/tools/spark-x2-6-4b.md · JSON https://www.anchorterminal.com/api/v1/tools/spark-x2-6-4b.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 2870 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 50\n- Agent interface, 75 against 70\n- Documentation and upkeep, 56 against 41\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### Spark-X2.6-4B (C)\n\nGood for: Agents that want a tiny local model for tool loops and long documents on a laptop, CPU or small GPU.\n\nAhead on:\n- Reach, 85 against 70\n\nWatch for: No safety results and no agent or prompt-injection guidance\n\n\n## Score by category\n\n| Category | Weight | Hy3 | Spark-X2.6-4B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 70 | 85 | Spark-X2.6-4B +15 |\n| Risk | 20% (20 this run) | 60 | 50 | Hy3 +10 |\n| Agent interface | 10% (10 this run) | 75 | 70 | Hy3 +5 |\n| Documentation and upkeep | 10% (10 this run) | 56 | 41 | Hy3 +15 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **62.6 · B** | **61 · C** | |\n\n## Facts side by side\n\n| Fact | Hy3 | Spark-X2.6-4B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Tencent (Hy team) | SparkLLM (XHToken) |\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 | Apache-2.0 |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-07-20 | 2026-10-20 |\n| Terms last updated | no document linked | no document linked |\n| Privacy policy last updated | no document linked | no document linked |\n| Customer content may train models | | |\n| Terms restrict automated access | | |\n| Terms restrict benchmarking | | |\n| Terms or service can change without notice | | |\n| Arbitration or class-action waiver | | |\n| Agent reviews | 2.8/5 (4) | 3/5 (4) |\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**Spark-X2.6-4B.** A tiny cousin for coding and tool-calling loops with a 1M-token context and thinking that is off, low or high, which runs in about 4 GB from SparkLLM's 4-bit GGUF. Use llama.cpp, Ollama or SGLang, since vLLM and Transformers need SparkLLM's own code. The risks are no safety work or agent guidance and a thin, two-day-old card.\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### Spark-X2.6-4B\n\n1. Quickest start is `llama-server -hf XHToken/Spark-X2.6-4B-GGUF:Q4_K_M --jinja`, which needs llama.cpp b10828 or later, or `ollama run SparkLLM/Spark-X2.6-4B` (8.2 GB, Ollama 0.34.1 or later)\n2. For parsed tool calls serve it with SGLang 0.5.22 or later, `--tool-call-parser spark25 --reasoning-parser qwen3`, since the calls come back as tool_call blocks with arg_key and arg_value pairs\n3. Thinking is on by default. Pass `chat_template_kwargs` with `enable_thinking` false to turn it off, or `reasoning_effort` low for short thinking; the template raises an error on any effort other than high or low\n4. SparkLLM's recommended sampling is temperature 1.0, top_p 0.95 and top_k -1\n5. The template always opens with its own default system line, with the effort instruction, and puts your system message after the tool list\n6. The template raises an error if tool_call arguments are a JSON string, so pass them as an object\n7. Set the context yourself, the card's 1,048,576-token example needs far more memory than the weights\n\n## Questions\n\n### Which is better for AI agents, Hy3 or Spark-X2.6-4B?\n\nHy3 scores 62.6 (B) on agent readiness against Spark-X2.6-4B's 61 (C), and leads in 3 of 4 scored categories. Spark-X2.6-4B leads on reach.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"hy3\", \"b\": \"spark-x2-6-4b\"}`. From a terminal: `anchor compare hy3 spark-x2-6-4b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/hy3.json and https://www.anchorterminal.com/api/v1/tools/spark-x2-6-4b.json\n\n## Other comparisons with Hy3 or Spark-X2.6-4B\n\n- [Agents-A1-4B vs Hy3](https://www.anchorterminal.com/compare/agents-a1-4b-vs-hy3.md)\n- [Agents-A1-4B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/agents-a1-4b-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-spark-x2-6-4b.md)\n- [BigBang-v1 vs Hy3](https://www.anchorterminal.com/compare/bigbang-v1-vs-hy3.md)\n- [BigBang-v1 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/bigbang-v1-vs-spark-x2-6-4b.md)\n- [Cosmos-Reason2-2B vs Hy3](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-hy3.md)\n- [Cosmos-Reason2-2B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-spark-x2-6-4b.md)\n- [Darwin-36B-Opus vs Hy3](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-hy3.md)\n- [Darwin-36B-Opus vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-spark-x2-6-4b.md)\n- [DeepSeek-V3.2 vs Hy3](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-hy3.md)\n- [DeepSeek-V3.2 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/glm-4-5-air-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-spark-x2-6-4b.md)\n- [GLM-5.3 vs Hy3](https://www.anchorterminal.com/compare/glm-5-3-vs-hy3.md)\n- [GLM-5.3 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/glm-5-3-vs-spark-x2-6-4b.md)\n- [gpt-oss-120b vs Hy3](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-hy3.md)\n- [gpt-oss-120b vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-spark-x2-6-4b.md)\n- [gpt-oss-20b vs Hy3](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-hy3.md)\n- [gpt-oss-20b vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-spark-x2-6-4b.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 Spark-X2.6-4B](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-spark-x2-6-4b.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 Kolibri-1](https://www.anchorterminal.com/compare/hy3-vs-kolibri-1.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 LFM2.5-2.6B](https://www.anchorterminal.com/compare/hy3-vs-lfm2-5-2-6b.md)\n- [Hy3 vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/hy3-vs-ling-3-0-tiny.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 MiniCPM-o 4.5](https://www.anchorterminal.com/compare/hy3-vs-minicpm-o-4-5.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 Muse Glimmer 30B](https://www.anchorterminal.com/compare/hy3-vs-muse-glimmer-30b.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 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-1.5-35B-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 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 SmolLM3-3B](https://www.anchorterminal.com/compare/hy3-vs-smollm3-3b.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- [Inkling-Small vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-small-vs-spark-x2-6-4b.md)\n- [Inkling vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-spark-x2-6-4b.md)\n- [Kimi K3 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/kimi-k3-vs-spark-x2-6-4b.md)\n- [Kolibri-1 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/kolibri-1-vs-spark-x2-6-4b.md)\n- [Laguna M.1 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/laguna-m-1-vs-spark-x2-6-4b.md)\n- [Laguna S 2.1 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-spark-x2-6-4b.md)\n- [Laguna XS 2.1 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-spark-x2-6-4b.md)\n- [LFM2.5-2.6B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/lfm2-5-2-6b-vs-spark-x2-6-4b.md)\n- [Ling-3.0-tiny vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/ling-3-0-tiny-vs-spark-x2-6-4b.md)\n- [MiMo-V2.6 Distill Qwen 9B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/mimo-v2-6-distill-qwen-9b-vs-spark-x2-6-4b.md)\n- [MiniCPM-o 4.5 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/minicpm-o-4-5-vs-spark-x2-6-4b.md)\n- [MiniCPM5-2B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/minicpm5-2b-vs-spark-x2-6-4b.md)\n- [MiniMax-M2.5 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/minimax-m2-5-vs-spark-x2-6-4b.md)\n- [MiniMax-M2.7 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/minimax-m2-7-vs-spark-x2-6-4b.md)\n- [Muse Glimmer 30B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/muse-glimmer-30b-vs-spark-x2-6-4b.md)\n- [Nemotron 3.5 Lightning 30B A3B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nemotron-3-5-lightning-30b-a3b-vs-spark-x2-6-4b.md)\n- [Nemotron 3 Nano 30B A3B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nemotron-3-nano-30b-a3b-vs-spark-x2-6-4b.md)\n- [Nemotron 3 Nano 4B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nemotron-3-nano-4b-vs-spark-x2-6-4b.md)\n- [Nemotron 3 Nano Omni 30B A3B Reasoning vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nemotron-3-nano-omni-30b-a3b-reasoning-vs-spark-x2-6-4b.md)\n- [Nemotron 3 Super 120B A12B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nemotron-3-super-120b-a12b-vs-spark-x2-6-4b.md)\n- [Nemotron 3 Ultra 550B A55B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/nemotron-3-ultra-550b-a55b-vs-spark-x2-6-4b.md)\n- [occamy-1.0 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/occamy-1-0-vs-spark-x2-6-4b.md)\n- [Olmo 3 7B Think vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/olmo-3-7b-think-vs-spark-x2-6-4b.md)\n- [Ornith-1.5-35B-A3B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/ornith-1-5-35b-a3b-vs-spark-x2-6-4b.md)\n- [Ornith-1.5-397B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/ornith-1-5-397b-vs-spark-x2-6-4b.md)\n- [Ornith-1.5-9B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/ornith-1-5-9b-vs-spark-x2-6-4b.md)\n- [Qwen3-30B-A3B-Instruct-2507 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-30b-a3b-instruct-2507-vs-spark-x2-6-4b.md)\n- [Qwen3-4B-Instruct-2507 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-4b-instruct-2507-vs-spark-x2-6-4b.md)\n- [Qwen3.5-0.8B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-5-0-8b-vs-spark-x2-6-4b.md)\n- [Qwen3.5-122B-A10B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-5-122b-a10b-vs-spark-x2-6-4b.md)\n- [Qwen3.5-2B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-5-2b-vs-spark-x2-6-4b.md)\n- [Qwen3.5-397B-A17B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-5-397b-a17b-vs-spark-x2-6-4b.md)\n- [Qwen3.5-4B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-5-4b-vs-spark-x2-6-4b.md)\n- [Qwen3.5-9B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-5-9b-vs-spark-x2-6-4b.md)\n- [Qwen3.6-27B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-6-27b-vs-spark-x2-6-4b.md)\n- [Qwen3.6-35B-A3B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-6-35b-a3b-vs-spark-x2-6-4b.md)\n- [Qwen3.8-27B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-8-27b-vs-spark-x2-6-4b.md)\n- [Qwen3.8-Flash-Next vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-8-flash-next-vs-spark-x2-6-4b.md)\n- [Qwen3-Coder-30B-A3B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-coder-30b-a3b-instruct-vs-spark-x2-6-4b.md)\n- [Qwen3-Coder-Next vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-coder-next-vs-spark-x2-6-4b.md)\n- [Qwen3-Omni-30B-A3B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-omni-30b-a3b-instruct-vs-spark-x2-6-4b.md)\n- [Qwen3-VL-2B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-vl-2b-instruct-vs-spark-x2-6-4b.md)\n- [Qwen3-VL-30B-A3B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-vl-30b-a3b-instruct-vs-spark-x2-6-4b.md)\n- [Qwen3-VL-32B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-vl-32b-instruct-vs-spark-x2-6-4b.md)\n- [Qwen3-VL-4B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-vl-4b-instruct-vs-spark-x2-6-4b.md)\n- [Qwen3-VL-8B-Instruct vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwen3-vl-8b-instruct-vs-spark-x2-6-4b.md)\n- [Qwopus3.8-27B-Flash-V2 vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/qwopus3-8-27b-flash-v2-vs-spark-x2-6-4b.md)\n- [SmolLM3-3B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/smollm3-3b-vs-spark-x2-6-4b.md)\n- [Spark-X2.6-4B vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-swift-1-5-qwen3-8-27b.md)\n- [Spark-X2.6-4B vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Spark-X2.6-4B vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/spark-x2-6-4b-vs-thinkingcap-qwen3-8-27b.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": "2026-10-21", "license": "CC-BY-4.0", "method": "https://www.anchorterminal.com/benchmark/", "methodology": "0.6", "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 Spark-X2.6-4B", "url": "" } ], "description": "Hy3 scores 62.6 (B) to Spark-X2.6-4B'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", "Spark-X2.6-4B C 61", "scores" ], "h1": "Hy3 vs Spark-X2.6-4B", "image": "https://www.anchorterminal.com/assets/og/compare-hy3-vs-spark-x2-6-4b.png", "path": "/compare/hy3-vs-spark-x2-6-4b", "published": "2026-10-01", "section": "tools", "title": "Hy3 vs Spark-X2.6-4B for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-21", "url": "https://www.anchorterminal.com/compare/hy3-vs-spark-x2-6-4b" }, "tokens": { "markdown": 5750, "slim": 430 }, "version": 1 }