{ "data": { "a": { "slug": "inkling", "name": "Inkling", "vendor": "Thinking Machines Lab", "vendorUrl": "https://thinkingmachines.ai", "kind": "weights", "category": "open-weights", "summary": "Inkling is Thinking Machines Lab's large open-weight mixture-of-experts model, 975B total and 41B active parameters, taking text, images and audio and returning text, with adjustable thinking effort, published in BF16 and NVFP4 under Apache 2.0.", "url": "https://www.anchorterminal.com/tools/inkling", "markdownUrl": "https://www.anchorterminal.com/tools/inkling.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/inkling.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/inkling.json", "repo": "https://huggingface.co/thinkingmachines/Inkling", "license": "Apache-2.0", "transports": [], "packages": [ { "registry": "huggingface", "name": "thinkingmachines/Inkling" }, { "registry": "huggingface", "name": "thinkingmachines/Inkling-NVFP4" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. Neither repository is gated (checked 2026-10-21). Thinking Machines' Model Acceptable Use Policy, linked from the card, says that downloading or using the weights binds you to it.", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0 with Thinking Machines' Model Acceptable Use Policy on top. Running it yourself costs the hardware, 1,904.8 GB for the BF16 files and 592.0 GB for the NVFP4 build. Thinking Machines' Tinker serves it as a beta serverless inference API at $1.00 per million input tokens and $4.05 per million output tokens (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://thinkingmachines.ai/model-card/inkling/", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "moe", "multimodal", "audio", "reasoning", "tool-calling", "apache-2.0", "safetensors", "nvfp4", "self-hosted" ], "lastRelease": "2026-07-23", "graded": true, "anchor": { "graded": true, "score": 64.2, "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": 1217, "categoryRank": 16, "methodology": "0.6", "run": "2026-10-01", "scores": { "capability": 60, "interface": 85, "reach": 50, "risk": 70, "upkeep": 82 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "high", "date": "2026-10-21" }, "negative": 0, "verdict": "Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.", "bestFor": "Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.", "strengths": [ "Three inference providers and Thinking Machines' own Tinker host it today", "Safetensors only, with a checksum on every LFS file in the publisher's own organisation", "Thinking effort set per request, several tool calls a turn and a 1M-token context", "Released support in Transformers, vLLM and SGLang, with inkling tool and reasoning parsers", "Thinking Machines answered 8 of the 13 questions and reports in its discussions", "A training-content summary with sources, mix and a July 2026 collection cut-off" ], "weaknesses": [ "The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation", "Apache 2.0 comes with an acceptable use policy that binds on download and can change at any time", "No release of ggml-org's llama.cpp, Ollama or LM Studio runs it", "Safety results are Thinking Machines' own, with no harness to rerun them and no prompt-injection guidance", "Structured output isn't documented, and the card gives no dated knowledge cut-off" ], "agentNotes": [ "Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it", "On 8 B200 GPUs, SGLang's recipe is `sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling`", "Use the inkling tool parser, not Hermes, and the inkling reasoning parser", "Pass `reasoning_effort` as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh", "Tool call arguments must reach the template as an object, not a JSON string, or it raises an error", "Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card", "Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 4, "avgRating": 3, "history": [ { "basis": "public evidence", "confidence": "high", "grade": "B", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 64.2 } ], "editorialScores": { "capability": 60, "interface": 85, "reach": 50, "risk": 70, "upkeep": 82 }, "provenanceScore": 67, "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": "# per SGLang's cookbook, NVFP4 on 8 B200 GPUs:\nsglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 \\\n --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling", "http": "curl http://localhost:30000/v1/chat/completions \\\n -H \"Content-Type: application/json\" \\\n -d '{\n \"model\": \"thinkingmachines/Inkling-NVFP4\",\n \"messages\": [{\"role\": \"user\", \"content\": \"Hello!\"}],\n \"reasoning_effort\": \"low\"\n }'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/inkling" }, "sameCompany": [ "inkling-small" ], "sameModel": [ "tinker" ], "weights": { "trainedBy": "Thinking Machines Lab", "params": "975B", "active": "41B", "context": 1048576, "goodFor": "Large mixture-of-experts generalist for coding, agents, factual recall and audio, with images in and thinking effort set per request.", "runtimes": [ "vLLM", "SGLang", "Transformers" ], "builds": [ { "name": "Inkling-NVFP4", "url": "https://huggingface.co/thinkingmachines/Inkling-NVFP4", "who": "publisher", "precision": "nvfp4", "sizeGB": 592, "memoryGB": 1024, "format": "safetensors", "note": "NVFP4 experts with FP8 and BF16 parts. Thinking Machines says W4A4 needs NVIDIA SM100 or newer, and W4A16 runs on H200" }, { "name": "Inkling", "url": "https://huggingface.co/thinkingmachines/Inkling", "who": "publisher", "precision": "bf16", "sizeGB": 1904.8, "memoryGB": 4096, "format": "safetensors", "note": "1,904.8 GB × 1.2 = 2,285.7 GB, so the 4,096 GB band. Thinking Machines states at least 2 TB of GPU memory" } ], "run": "sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling", "runBuild": "Inkling-NVFP4", "checked": "2026-10-21", "minMemoryGB": 1024 }, "family": { "lab": "Thinking Machines Lab", "family": "Inkling", "url": "https://www.anchorterminal.com/open-weights/#thinking-machines", "others": [ { "name": "Inkling-Small", "url": "https://huggingface.co/thinkingmachines/Inkling-Small", "params": "265.96B (Hub safetensors count; the name states none)", "listing": "https://www.anchorterminal.com/tools/inkling-small" } ], "unrestrictedCopies": 1 }, "area": "models", "provenance": { "legalEntity": "Thinking Machines Lab, Inc. (named on its model card page and in its training-content summary)", "domain": "thinkingmachines.ai", "domainRegistered": "", "domainNote": "thinkingmachines.ai's registration date wasn't read on 21 October 2026.", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/thinkingmachines/Inkling/commits/main", "securityTxt": "valid", "checked": "2026-10-21", "notes": [ "Thinking Machines' Inkling page links the thinkingmachines collection on Hugging Face, and its model card page links the repository. Hugging Face hasn't verified the organisation.", "Nothing is hosted for this listing, so the Apache 2.0 licence and the Model Acceptable Use Policy stand in for terms of service and no privacy policy is scored.", "The changelog is the repository's commit history, 13 commits from 15 to 23 July 2026, the upload, a Transformers processor and template change on 15 July, card updates and community evaluation results.", "thinkingmachines.ai/.well-known/security.txt gives a security contact, a PGP key and an expiry in 2029, and the site publishes a coordinated vulnerability disclosure policy that leaves model safety to a separate incident contact." ], "score": 67 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/inkling.json", "live": { "slug": "inkling", "securityTxt": { "url": "https://thinkingmachines.ai/.well-known/security.txt", "state": "valid", "expires": "2029-07-13T07:00:00.000Z", "checkedAt": "2026-10-27T15:31:10.758234557Z" }, "domain": { "domain": "thinkingmachines.ai", "registered": "2024-07-09", "source": "https://rdap.identitydigital.services/rdap/domain/thinkingmachines.ai", "checkedAt": "2026-10-25T14:03:35.628227784Z" }, "pages": [ { "url": "https://huggingface.co/thinkingmachines/Inkling/commits/main", "kind": "changelog", "status": 200, "checkedAt": "2026-10-27T03:49:15.764649928Z", "changedAt": "2026-10-27T03:49:15.764649928Z", "fingerprint": "185f38ac0050" } ], "updatedAt": "2026-10-27T15:31:10.758234557Z" } }, "answer": "Inkling scores 64.2 (B) on agent readiness against LBS-27B's 53.9 (D), and leads in 3 of 4 scored categories. LBS-27B leads on reach.", "b": { "slug": "lbs-27b", "name": "LBS-27B", "vendor": "inclusionAI (Ant Group)", "vendorUrl": "https://www.inclusion-ai.org", "kind": "weights", "category": "open-weights", "summary": "LBS-27B is an open-weight vision-language model from inclusionAI's UI-Venus line, fine-tuned from Qwen3.8-27B to find what to click on a screenshot by zooming into regions over several turns, and applied to visual questions on large images.", "url": "https://www.anchorterminal.com/tools/lbs-27b", "markdownUrl": "https://www.anchorterminal.com/tools/lbs-27b.md", "slimMarkdownUrl": "https://www.anchorterminal.com/tools/lbs-27b.min.md", "jsonUrl": "https://www.anchorterminal.com/api/v1/tools/lbs-27b.json", "repo": "https://huggingface.co/inclusionAI/LBS-27B", "license": "Apache-2.0 (the card's metadata and licence section; the LICENSE file sits in the GitHub repository inclusionAI/UI-Venus on its LBS branch, not in the Hugging Face repository)", "transports": [], "packages": [ { "registry": "huggingface", "name": "inclusionAI/LBS-27B" } ], "auth": "none", "authNotes": "The weights download from Hugging Face with no account, token or terms to accept. The Hub reports gated false for inclusionAI/LBS-27B (checked 2026-10-27).", "pricing": "free", "pricingNotes": "Free to download and use, commercial use included, under Apache 2.0 as the card states for the weights and the code. Running it costs the hardware, 54.73 GB of BF16 files and no quantised build from the publisher. No hosted API or inference provider serves it (checked 2026-10-27).", "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 2026-10-27).", "endpoints": [] }, "toolCount": null, "popularity": { "githubStars": null, "npmWeekly": null, "pypiWeekly": null, "asOf": "2026-10-27" }, "docsUrl": "https://github.com/inclusionAI/UI-Venus/tree/LBS", "capabilities": [ "model.open-weights" ], "tags": [ "open-weights", "model", "dense", "qwen", "vision", "gui-grounding", "computer-use", "reasoning", "safetensors", "self-hosted", "new" ], "lastRelease": "2026-10-26", "graded": true, "anchor": { "graded": true, "score": 53.9, "grade": "D", "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": 1217, "categoryRank": 73, "methodology": "0.6", "run": "2026-10-01", "scores": { "interface": 70, "reach": 55, "risk": 50, "upkeep": 43 }, "pending": [ "performance", "tasks" ], "assessment": { "confidence": "low", "date": "2026-10-27" }, "negative": 0, "verdict": "A 27B Qwen3.8 fine-tune for GUI grounding that zooms into screenshots over a few turns before naming a point, and inclusionAI says it also helps with fine detail in large images. It needs about 96 GB at BF16 and a client that runs its crop actions. Every result so far is inclusionAI's own, with no safety results or injection guidance.", "bestFor": "Agents with about 96 GB of GPU memory that need to find click targets on dense professional screenshots, or read fine detail in large images, and can run a small crop loop and wait for independent results.", "strengths": [ "Qwen3.8-27B's stock architecture with no repository code, so released vLLM, SGLang, Transformers and llama.cpp load it", "Apache 2.0 for the weights and the base, ungated, safetensors only", "A simple, documented plain-text crop protocol with a point answer on a 0 to 1000 scale, and the training recipe and evaluation kit published", "Up to two crops per turn, learned in GRPO, and 262,144 tokens of context from the base", "inclusionAI publishes per-item scores and selected trajectories for its own benchmark runs" ], "weaknesses": [ "No independent benchmark result yet; ScreenSpot-Pro, OS-World-G, PerceptionBench and HR-Bench numbers are inclusionAI's own runs", "BF16 only, about 66 GB to load, and no Ollama, LM Studio or quantised build", "The crop loop and system prompt come from the publisher's Python, not a runtime parser or a template", "No safety evaluation, prompt-injection guidance, training data sources or knowledge cut-off", "No hosted API or inference provider serves it" ], "agentNotes": [ "Serve with `vllm serve inclusionAI/LBS-27B --tensor-parallel-size 4 --max-model-len 65536`, which is what the card's wrapper script runs; keep the context at 32,768 or more for multi-turn images", "Build the system prompt with `build_system_prompt` from the LBS branch's `zoomin_grounding_protocol.py`, send the screenshot after `image_path: \u003cname\u003e`, and don't pass `tools`; the model answers in plain text", "Parse `\u003caction\u003ecrop_image(image_path=..., x1=..., y1=..., x2=..., y2=...)\u003c/action\u003e`, cut the crop yourself and return it with its mapping to the original image; allow at most two crops per turn and three per episode", "Read the final answer as `[x.xx,y.yy]` on a 0 to 1000 scale of the original image, and use your own executor to click", "Pass `reasoning_effort` as `xhigh`, `medium` or `low` only, since the template raises an error for `high`, and don't count on `thinking_budget`, which the template ignores", "Don't turn on MTP speculative decoding; the MTP weights aren't in the repository though config.json names one MTP layer" ], "metrics": { "kind": "local", "measured": false }, "reviewCount": 0, "avgRating": 0, "history": [ { "basis": "public evidence", "confidence": "low", "grade": "D", "methodology": "0.6", "pending": [ "performance", "tasks" ], "run": "2026-10-01", "runLabel": "October 2026 research run", "score": 53.9 } ], "editorialScores": { "interface": 70, "reach": 55, "risk": 50, "upkeep": 43 }, "provenanceScore": 57, "checked": { "categories": { "interface": "2026-10-27", "reach": "2026-10-27", "risk": "2026-10-27", "upkeep": "2026-10-27" }, "last": "2026-10-27", "oldest": "2026-10-27", "stale": false, "staleAfterDays": 90 } }, "connect": { "install": "# The card's route clones the LBS branch and wraps vllm serve (four GPUs in its example)\ngit clone --branch LBS --single-branch https://github.com/inclusionAI/UI-Venus.git\ncd UI-Venus/evaluation\nbash scripts/serve_vllm.sh start inclusionAI/LBS-27B --name lbs --tp 4 --dp 1 --daemon\n# the same server without the wrapper (the script's defaults are a 65,536-token context and 64 sequences)\nvllm serve inclusionAI/LBS-27B --served-model-name lbs --tensor-parallel-size 4 --max-model-len 65536", "http": "curl http://localhost:8000/v1/chat/completions -H 'Content-Type: application/json' \\\n -d '{\"model\": \"lbs\", \"max_tokens\": 2560,\n \"messages\": [{\"role\": \"system\", \"content\": \"\u003ctask, image size, crop_image spec and answer format, as build_system_prompt in the LBS branch writes them\u003e\"},\n {\"role\": \"user\", \"content\": [{\"type\": \"text\", \"text\": \"image_path: screenshot.png\"},\n {\"type\": \"image_url\", \"image_url\": {\"url\": \"data:image/png;base64,...\"}}]}],\n \"chat_template_kwargs\": {\"reasoning_effort\": \"xhigh\"}}'" }, "letme": { "capability": "https://letme.dev/model.open-weights", "tool": "https://letme.dev/lbs-27b" }, "sameCompany": [ "ming-3-0-asr-tiny", "ming-3-0-audio-flash", "ming-3-0-audio-tiny", "ming-3-0-tts-tiny", "ling-3-0-tiny" ], "weights": { "trainedBy": "inclusionAI (Ant Group), with Wuhan University of Technology, CASIA and Zhejiang University", "builtOn": "Qwen/Qwen3.8-27B (fine-tune, named in the card's text, not in its base_model metadata; Apache 2.0, copyright Alibaba Cloud)", "params": "27B", "context": 262144, "goodFor": "A cousin that finds the point to click on a screenshot, and answers questions about fine detail in large images, by zooming in over a few turns, on a machine with about 96 GB of memory and a client that runs the crops, if inclusionAI's own results hold up.", "runtimes": [ "vLLM", "SGLang", "Transformers", "llama.cpp" ], "builds": [ { "name": "LBS-27B (BF16)", "url": "https://huggingface.co/inclusionAI/LBS-27B", "who": "publisher", "precision": "bf16", "sizeGB": 54.73, "memoryGB": 96, "format": "safetensors", "runsOn": [ "vLLM", "SGLang", "Transformers" ], "note": "Whole repository, 54.73 GB, almost all of it 12 BF16 shards. 54.73 GB × 1.2 = 65.7 GB, just over 64 GB. The only build; no Ollama, LM Studio or ggml-org build and no copy by anyone else on 27 October 2026" } ], "run": "vllm serve inclusionAI/LBS-27B --served-model-name lbs --tensor-parallel-size 4 --max-model-len 65536", "runBuild": "LBS-27B (BF16)", "checked": "2026-10-27", "minMemoryGB": 96 }, "family": { "lab": "inclusionAI (Ant Group)", "family": "UI-Venus", "url": "https://www.anchorterminal.com/open-weights/#inclusionai", "others": [ { "name": "UI-Venus-2-9B", "url": "https://huggingface.co/inclusionAI/UI-Venus-2-9B", "params": "9B" }, { "name": "UI-Venus-1.5-30B-A3B", "url": "https://huggingface.co/inclusionAI/UI-Venus-1.5-30B-A3B", "params": "30B total, 3B active" }, { "name": "UI-Venus-1.5-8B", "url": "https://huggingface.co/inclusionAI/UI-Venus-1.5-8B", "params": "8B" }, { "name": "UI-Venus-1.5-2B", "url": "https://huggingface.co/inclusionAI/UI-Venus-1.5-2B", "params": "2B" } ], "olderCount": 54 }, "area": "models", "provenance": { "legalEntity": "inclusionAI, Ant Group (named in the site footer of inclusion-ai.org); the work is credited to authors from Wuhan University of Technology, CASIA, Zhejiang University and Ant Group", "domain": "inclusion-ai.org", "domainRegistered": "2025-04-03", "endpointOnVendorDomain": null, "terms": "", "privacy": "", "statusPage": "", "changelog": "https://huggingface.co/inclusionAI/LBS-27B/commits/main", "securityTxt": "none", "checked": "2026-10-27", "notes": [ "inclusion-ai.org links to huggingface.co/inclusionAI and github.com/inclusionAI (read 2026-10-27). The Hub doesn't verify the organisation, which the calibration of 21 October credits as the publisher's own. The domain registration date is carried from the Ming-3.0 listings' check of 21 October 2026.", "The model card links github.com/inclusionAI/UI-Venus on its LBS branch, where the LICENSE, the NOTICE, the training recipe and the evaluation kit sit. The NOTICE reads Copyright 2026 the LBS contributors.", "Nothing is hosted, so the Apache 2.0 licence stands in for terms of service and no privacy policy is scored.", "The changelog is the Hugging Face commit history, two commits on 26 October 2026 (initial commit and one upload).", "inclusion-ai.org/.well-known/security.txt reset the connection on 27 October 2026 and answered 404 on 21 October. The LBS branch has no SECURITY.md. Ant Group runs a company-wide security response centre, AntSRC (https://security.alipay.com/, answering on 27 October 2026); nothing on the card or the branch links it." ], "score": 57 }, "pageJsonUrl": "https://www.anchorterminal.com/tools/lbs-27b.json", "live": { "slug": "lbs-27b", "securityTxt": { "url": "https://inclusion-ai.org/.well-known/security.txt", "state": "unknown", "checkedAt": "2026-10-27T15:31:25.810013407Z" }, "updatedAt": "2026-10-27T15:31:25.810013407Z" } }, "facts": [ { "a": "Open-weight model", "b": "Open-weight model", "name": "Kind" }, { "a": "Thinking Machines Lab", "b": "inclusionAI (Ant Group)", "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 (the card's metadata and licence section; the LICENSE file sits in the GitHub repository inclusionAI/UI-Venus on its LBS branch, not in the Hugging Face repository)", "name": "Licence" }, { "a": "no", "b": "no", "name": "Read-only variant documented" }, { "a": "no", "b": "no", "name": "llms.txt" }, { "a": "2026-07-23", "b": "2026-10-26", "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": "3/5 (4)", "b": "none", "name": "Agent reviews" } ], "faq": [ { "answer": "Inkling scores 64.2 (B) on agent readiness against LBS-27B's 53.9 (D), and leads in 3 of 4 scored categories. LBS-27B leads on reach.", "question": "Which is better for AI agents, Inkling or LBS-27B?" } ], "goodFor": [ { "aheadOn": [ "Risk, 70 against 50", "Agent interface, 85 against 70", "Documentation and upkeep, 82 against 43" ], "also": null, "goodFor": "Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.", "slug": "inkling", "watchFor": "The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation" }, { "aheadOn": [ "Reach, 55 against 50" ], "also": null, "goodFor": "Agents with about 96 GB of GPU memory that need to find click targets on dense professional screenshots, or read fine detail in large images, and can run a small crop loop and wait for independent results.", "slug": "lbs-27b", "watchFor": "No independent benchmark result yet; ScreenSpot-Pro, OS-World-G, PerceptionBench and HR-Bench numbers are inclusionAI's own runs" } ], "job": { "capability": "model.open-weights", "name": "Open-weight models you run yourself" }, "others": [ { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling.json", "title": "Agents-A1-4B vs Inkling", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-lbs-27b.json", "title": "Agents-A1-4B vs LBS-27B", "url": "https://www.anchorterminal.com/compare/agents-a1-4b-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling.json", "title": "Apertus v1.5 8B vs Inkling", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lbs-27b.json", "title": "Apertus v1.5 8B vs LBS-27B", "url": "https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling.json", "title": "Apodex-1.1-mini vs Inkling", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lbs-27b.json", "title": "Apodex-1.1-mini vs LBS-27B", "url": "https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling.json", "title": "BigBang-v1 vs Inkling", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/bigbang-v1-vs-lbs-27b.json", "title": "BigBang-v1 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/bigbang-v1-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling.json", "title": "Carbon-X vs Inkling", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/carbon-x-vs-lbs-27b.json", "title": "Carbon-X vs LBS-27B", "url": "https://www.anchorterminal.com/compare/carbon-x-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling.json", "title": "Cosmos-Reason2-2B vs Inkling", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lbs-27b.json", "title": "Cosmos-Reason2-2B vs LBS-27B", "url": "https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling.json", "title": "Darwin-36B-Opus vs Inkling", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lbs-27b.json", "title": "Darwin-36B-Opus vs LBS-27B", "url": "https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.json", "title": "DeepSeek-V3.2 vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lbs-27b.json", "title": "DeepSeek-V3.2 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling.json", "title": "DeepSeek V4.1 Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lbs-27b.json", "title": "DeepSeek V4.1 Flash vs LBS-27B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling.json", "title": "DeepSeek-V4-Flash-0731 vs Inkling", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lbs-27b.json", "title": "DeepSeek-V4-Flash-0731 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.json", "title": "DiffusionGemma 26B A4B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lbs-27b.json", "title": "DiffusionGemma 26B A4B IT vs LBS-27B", "url": "https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling.json", "title": "Gemma 4 12B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lbs-27b.json", "title": "Gemma 4 12B IT vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling.json", "title": "Gemma 4 26B A4B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lbs-27b.json", "title": "Gemma 4 26B A4B IT vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling.json", "title": "Gemma 4 31B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lbs-27b.json", "title": "Gemma 4 31B IT vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling.json", "title": "Gemma 4 E2B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lbs-27b.json", "title": "Gemma 4 E2B IT vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling.json", "title": "Gemma 4 E4B IT vs Inkling", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lbs-27b.json", "title": "Gemma 4 E4B IT vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling.json", "title": "GLM-4.5-Air vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-lbs-27b.json", "title": "GLM-4.5-Air vs LBS-27B", "url": "https://www.anchorterminal.com/compare/glm-4-5-air-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling.json", "title": "GLM-4.7-Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lbs-27b.json", "title": "GLM-4.7-Flash vs LBS-27B", "url": "https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.json", "title": "GLM-5.3-Flash vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lbs-27b.json", "title": "GLM-5.3-Flash vs LBS-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.json", "title": "GLM-5.3 vs Inkling", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/glm-5-3-vs-lbs-27b.json", "title": "GLM-5.3 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/glm-5-3-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling.json", "title": "gpt-oss-120b vs Inkling", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lbs-27b.json", "title": "gpt-oss-120b vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.json", "title": "gpt-oss-20b vs Inkling", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lbs-27b.json", "title": "gpt-oss-20b vs LBS-27B", "url": "https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling.json", "title": "Granite 4.2 3B vs Inkling", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling" }, { "json": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lbs-27b.json", "title": "Granite 4.2 3B vs LBS-27B", "url": "https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lbs-27b" }, { "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-lbs-27b.json", "title": "Hy3 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/hy3-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-small-vs-lbs-27b.json", "title": "Inkling-Small vs LBS-27B", "url": "https://www.anchorterminal.com/compare/inkling-small-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-inkling-small.json", "title": "Inkling vs Inkling-Small", "url": "https://www.anchorterminal.com/compare/inkling-vs-inkling-small" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview.json", "title": "Inkling vs InternVL3.5-GPT-OSS-20B-A4B-Preview", "url": "https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-kimi-k3.json", "title": "Inkling vs Kimi K3", "url": "https://www.anchorterminal.com/compare/inkling-vs-kimi-k3" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-kolibri-1.json", "title": "Inkling vs Kolibri-1", "url": "https://www.anchorterminal.com/compare/inkling-vs-kolibri-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-kronos.json", "title": "Inkling vs Kronos", "url": "https://www.anchorterminal.com/compare/inkling-vs-kronos" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-laguna-m-1.json", "title": "Inkling vs Laguna M.1", "url": "https://www.anchorterminal.com/compare/inkling-vs-laguna-m-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-laguna-s-2-1.json", "title": "Inkling vs Laguna S 2.1", "url": "https://www.anchorterminal.com/compare/inkling-vs-laguna-s-2-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-laguna-xs-2-1.json", "title": "Inkling vs Laguna XS 2.1", "url": "https://www.anchorterminal.com/compare/inkling-vs-laguna-xs-2-1" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b.json", "title": "Inkling vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny.json", "title": "Inkling vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-distill-qwen-9b.json", "title": "Inkling vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5.json", "title": "Inkling vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minicpm5-2b.json", "title": "Inkling vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-5.json", "title": "Inkling vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-7.json", "title": "Inkling vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m3-1-flash.json", "title": "Inkling vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/inkling-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b.json", "title": "Inkling vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b.json", "title": "Inkling vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "Inkling vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "Inkling vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-30b-a3b.json", "title": "Inkling vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-4b.json", "title": "Inkling vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "Inkling vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-super-120b-a12b.json", "title": "Inkling vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-ultra-550b-a55b.json", "title": "Inkling vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-occamy-1-0.json", "title": "Inkling vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/inkling-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-olmo-3-7b-think.json", "title": "Inkling vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/inkling-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-35b-a3b.json", "title": "Inkling vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-397b.json", "title": "Inkling vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-9b.json", "title": "Inkling vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-30b-a3b-instruct-2507.json", "title": "Inkling vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-4b-instruct-2507.json", "title": "Inkling vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-0-8b.json", "title": "Inkling vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-122b-a10b.json", "title": "Inkling vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-2b.json", "title": "Inkling vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-397b-a17b.json", "title": "Inkling vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-4b.json", "title": "Inkling vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-9b.json", "title": "Inkling vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-27b.json", "title": "Inkling vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-35b-a3b.json", "title": "Inkling vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-27b.json", "title": "Inkling vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-flash-next.json", "title": "Inkling vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-30b-a3b-instruct.json", "title": "Inkling vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-next.json", "title": "Inkling vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-omni-30b-a3b-instruct.json", "title": "Inkling vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-2b-instruct.json", "title": "Inkling vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-30b-a3b-instruct.json", "title": "Inkling vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-32b-instruct.json", "title": "Inkling vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-4b-instruct.json", "title": "Inkling vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-8b-instruct.json", "title": "Inkling vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-qwopus3-8-27b-flash-v2.json", "title": "Inkling vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/inkling-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-recursive-flint.json", "title": "Inkling vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/inkling-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-smollm3-3b.json", "title": "Inkling vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/inkling-vs-smollm3-3b" }, { "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/inkling-vs-swift-1-5-qwen3-8-27b.json", "title": "Inkling vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-flash-next.json", "title": "Inkling vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-thinkingcap-qwen3-8-27b.json", "title": "Inkling vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/inkling-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2.json", "title": "Inkling vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2" }, { "json": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lbs-27b.json", "title": "InternVL3.5-GPT-OSS-20B-A4B-Preview vs LBS-27B", "url": "https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/kimi-k3-vs-lbs-27b.json", "title": "Kimi K3 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/kimi-k3-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/kolibri-1-vs-lbs-27b.json", "title": "Kolibri-1 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/kolibri-1-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/kronos-vs-lbs-27b.json", "title": "Kronos vs LBS-27B", "url": "https://www.anchorterminal.com/compare/kronos-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/laguna-m-1-vs-lbs-27b.json", "title": "Laguna M.1 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/laguna-m-1-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lbs-27b.json", "title": "Laguna S 2.1 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lbs-27b.json", "title": "Laguna XS 2.1 vs LBS-27B", "url": "https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lbs-27b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-lfm2-5-2-6b.json", "title": "LBS-27B vs LFM2.5-2.6B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-lfm2-5-2-6b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-ling-3-0-tiny.json", "title": "LBS-27B vs Ling-3.0-tiny", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-ling-3-0-tiny" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-mimo-v2-6-distill-qwen-9b.json", "title": "LBS-27B vs MiMo-V2.6 Distill Qwen 9B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-mimo-v2-6-distill-qwen-9b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-minicpm-o-4-5.json", "title": "LBS-27B vs MiniCPM-o 4.5", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-minicpm-o-4-5" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-minicpm5-2b.json", "title": "LBS-27B vs MiniCPM5-2B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-minicpm5-2b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m2-5.json", "title": "LBS-27B vs MiniMax-M2.5", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m2-5" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m2-7.json", "title": "LBS-27B vs MiniMax-M2.7", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m2-7" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m3-1-flash.json", "title": "LBS-27B vs MiniMax-M3.1-Flash", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m3-1-flash" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-muse-glimmer-30b.json", "title": "LBS-27B vs Muse Glimmer 30B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-muse-glimmer-30b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nanbeige-4-3-33b.json", "title": "LBS-27B vs Nanbeige4.3-33B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nanbeige-4-3-33b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-5-bolt-e4b-4gb.json", "title": "LBS-27B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-5-bolt-e4b-4gb" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-5-lightning-30b-a3b.json", "title": "LBS-27B vs Nemotron 3.5 Lightning 30B A3B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-5-lightning-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-30b-a3b.json", "title": "LBS-27B vs Nemotron 3 Nano 30B A3B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-30b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-4b.json", "title": "LBS-27B vs Nemotron 3 Nano 4B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-4b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.json", "title": "LBS-27B vs Nemotron 3 Nano Omni 30B A3B Reasoning", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-omni-30b-a3b-reasoning" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-super-120b-a12b.json", "title": "LBS-27B vs Nemotron 3 Super 120B A12B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-super-120b-a12b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-ultra-550b-a55b.json", "title": "LBS-27B vs Nemotron 3 Ultra 550B A55B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-ultra-550b-a55b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-occamy-1-0.json", "title": "LBS-27B vs occamy-1.0", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-occamy-1-0" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-olmo-3-7b-think.json", "title": "LBS-27B vs Olmo 3 7B Think", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-olmo-3-7b-think" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-35b-a3b.json", "title": "LBS-27B vs Ornith-1.5-35B-A3B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-397b.json", "title": "LBS-27B vs Ornith-1.5-397B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-397b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-9b.json", "title": "LBS-27B vs Ornith-1.5-9B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-9b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-30b-a3b-instruct-2507.json", "title": "LBS-27B vs Qwen3-30B-A3B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-30b-a3b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-4b-instruct-2507.json", "title": "LBS-27B vs Qwen3-4B-Instruct-2507", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-4b-instruct-2507" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-0-8b.json", "title": "LBS-27B vs Qwen3.5-0.8B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-0-8b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-122b-a10b.json", "title": "LBS-27B vs Qwen3.5-122B-A10B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-122b-a10b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-2b.json", "title": "LBS-27B vs Qwen3.5-2B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-2b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-397b-a17b.json", "title": "LBS-27B vs Qwen3.5-397B-A17B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-397b-a17b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-4b.json", "title": "LBS-27B vs Qwen3.5-4B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-4b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-9b.json", "title": "LBS-27B vs Qwen3.5-9B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-9b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-6-27b.json", "title": "LBS-27B vs Qwen3.6-27B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-6-27b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-6-35b-a3b.json", "title": "LBS-27B vs Qwen3.6-35B-A3B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-6-35b-a3b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-8-27b.json", "title": "LBS-27B vs Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-8-flash-next.json", "title": "LBS-27B vs Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-coder-30b-a3b-instruct.json", "title": "LBS-27B vs Qwen3-Coder-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-coder-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-coder-next.json", "title": "LBS-27B vs Qwen3-Coder-Next", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-coder-next" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-omni-30b-a3b-instruct.json", "title": "LBS-27B vs Qwen3-Omni-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-omni-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-2b-instruct.json", "title": "LBS-27B vs Qwen3-VL-2B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-2b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-30b-a3b-instruct.json", "title": "LBS-27B vs Qwen3-VL-30B-A3B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-30b-a3b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-32b-instruct.json", "title": "LBS-27B vs Qwen3-VL-32B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-32b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-4b-instruct.json", "title": "LBS-27B vs Qwen3-VL-4B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-4b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-8b-instruct.json", "title": "LBS-27B vs Qwen3-VL-8B-Instruct", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-8b-instruct" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwopus3-8-27b-flash-v2.json", "title": "LBS-27B vs Qwopus3.8-27B-Flash-V2", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-qwopus3-8-27b-flash-v2" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-recursive-flint.json", "title": "LBS-27B vs Recursive Flint", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-recursive-flint" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-smollm3-3b.json", "title": "LBS-27B vs SmolLM3-3B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-smollm3-3b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-spark-x2-6-4b.json", "title": "LBS-27B vs Spark-X2.6-4B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-spark-x2-6-4b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-swift-1-5-qwen3-8-27b.json", "title": "LBS-27B vs Swift 1.5 Qwen3.8-27B", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-swift-1-5-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-swift-1-5-qwen3-8-flash-next.json", "title": "LBS-27B vs Swift 1.5 Qwen3.8-Flash-Next", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-swift-1-5-qwen3-8-flash-next" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-thinkingcap-qwen3-8-27b.json", "title": "LBS-27B vs ThinkingCap (Qwen3.8 27B)", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-thinkingcap-qwen3-8-27b" }, { "json": "https://www.anchorterminal.com/compare/lbs-27b-vs-unlimited-ocr-2.json", "title": "LBS-27B vs Baidu Unlimited-OCR-2", "url": "https://www.anchorterminal.com/compare/lbs-27b-vs-unlimited-ocr-2" } ], "scores": [ { "key": "capability", "name": "Capability", "pending": true, "weight": 35 }, { "by": 5, "edge": "lbs-27b", "inkling": 50, "key": "reach", "lbs-27b": 55, "name": "Reach", "weight": 25 }, { "by": 20, "edge": "inkling", "inkling": 70, "key": "risk", "lbs-27b": 50, "name": "Risk", "weight": 20 }, { "by": 15, "edge": "inkling", "inkling": 85, "key": "interface", "lbs-27b": 70, "name": "Agent interface", "weight": 10 }, { "by": 39, "edge": "inkling", "inkling": 82, "key": "upkeep", "lbs-27b": 43, "name": "Documentation and upkeep", "weight": 10 } ], "summary": "Inkling scores 64.2 (B) on agent readiness against LBS-27B's 53.9 (D), and leads in 3 of 4 scored categories. LBS-27B leads on reach. Both do open-weight models you run yourself.", "tutorials": [], "verdicts": { "inkling": "Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.", "lbs-27b": "A 27B Qwen3.8 fine-tune for GUI grounding that zooms into screenshots over a few turns before naming a point, and inclusionAI says it also helps with fine detail in large images. It needs about 96 GB at BF16 and a client that runs its crop actions. Every result so far is inclusionAI's own, with no safety results or injection guidance." } }, "kind": "anchor.page", "links": { "api": "https://www.anchorterminal.com/api/v1/index.json", "html": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b", "json": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.json", "llms": "https://www.anchorterminal.com/llms.txt", "markdown": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.md", "mcp": "https://www.anchorterminal.com/mcp", "slim": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.min.md" }, "markdown": "Inkling scores 64.2 (B) on agent readiness against LBS-27B's 53.9 (D), and leads in 3 of 4 scored categories. LBS-27B leads on reach. Both do open-weight models you run yourself.\n\n- Inkling: grade B, 64.2/100, rank #21 of 113 open-weight models. Markdown https://www.anchorterminal.com/tools/inkling.md · JSON https://www.anchorterminal.com/api/v1/tools/inkling.json\n- LBS-27B: grade D, 53.9/100, rank #91 of 113 open-weight models. Markdown https://www.anchorterminal.com/tools/lbs-27b.md · JSON https://www.anchorterminal.com/api/v1/tools/lbs-27b.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 3504 open weights comparisons: https://www.anchorterminal.com/compare/open-weights/index.md\n\n## Which one, for what\n\n### Inkling (B)\n\nGood for: Agents calling a hosted open multimodal model with audio input, or teams with a multi-GPU datacentre node who want to run it themselves.\n\nAhead on:\n- Risk, 70 against 50\n- Agent interface, 85 against 70\n- Documentation and upkeep, 82 against 43\n\nWatch for: The smallest build Thinking Machines publishes needs about 710 GB, beyond any single workstation\n\n### LBS-27B (D)\n\nGood for: Agents with about 96 GB of GPU memory that need to find click targets on dense professional screenshots, or read fine detail in large images, and can run a small crop loop and wait for independent results.\n\nAhead on:\n- Reach, 55 against 50\n\nWatch for: No independent benchmark result yet; ScreenSpot-Pro, OS-World-G, PerceptionBench and HR-Bench numbers are inclusionAI's own runs\n\n\n## Score by category\n\n| Category | Weight | Inkling | LBS-27B | Edge |\n| --- | --- | --- | --- | --- |\n| Capability | 35%, pending | pending | pending | not scored in this run |\n| Reach | 25% (25 this run) | 50 | 55 | LBS-27B +5 |\n| Risk | 20% (20 this run) | 70 | 50 | Inkling +20 |\n| Agent interface | 10% (10 this run) | 85 | 70 | Inkling +15 |\n| Documentation and upkeep | 10% (10 this run) | 82 | 43 | Inkling +39 |\n| Negative events | ≤15 | 0 | 0 | |\n| **Total** | | **64.2 · B** | **53.9 · D** | |\n\n## Facts side by side\n\n| Fact | Inkling | LBS-27B |\n| --- | --- | --- |\n| Kind | Open-weight model | Open-weight model |\n| Vendor | Thinking Machines Lab | inclusionAI (Ant Group) |\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 (the card's metadata and licence section; the LICENSE file sits in the GitHub repository inclusionAI/UI-Venus on its LBS branch, not in the Hugging Face repository) |\n| Read-only variant documented | no | no |\n| llms.txt | no | no |\n| Last release | 2026-07-23 | 2026-10-26 |\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 | 3/5 (4) | none |\n\n## Verdicts\n\n**Inkling.** Thinking Machines' large multimodal generalist, stronger than Inkling-Small on factual recall by its own numbers. It needs about 710 GB of datacentre GPU memory even in NVFP4, so most agents will use a host such as Together AI or Tinker. The main risks are a use policy that binds on download and can change, and no outside safety results.\n\n**LBS-27B.** A 27B Qwen3.8 fine-tune for GUI grounding that zooms into screenshots over a few turns before naming a point, and inclusionAI says it also helps with fine detail in large images. It needs about 96 GB at BF16 and a client that runs its crop actions. Every result so far is inclusionAI's own, with no safety results or injection guidance.\n\n## Before you call either\n\n### Inkling\n\n1. Unless you have a multi-GPU Blackwell or H200 node, call it through Together AI, Fireworks, DeepInfra or Tinker rather than starting it\n2. On 8 B200 GPUs, SGLang's recipe is `sglang serve --trust-remote-code --model-path thinkingmachines/Inkling-NVFP4 --tp 8 --quantization modelopt_fp4 --enable-multimodal --reasoning-parser inkling --tool-call-parser inkling`\n3. Use the inkling tool parser, not Hermes, and the inkling reasoning parser\n4. Pass `reasoning_effort` as none, minimal, low, medium, high (the default) or max, or a number from 0 to 0.99. The repository's template has no xhigh preset and raises an error for it, though Thinking Machines' docs list xhigh\n5. Tool call arguments must reach the template as an object, not a JSON string, or it raises an error\n6. Audio should be 16 kHz WAV, ideally under 20 minutes, and images 40 to 4096 px a side, per the card\n7. Read the Model Acceptable Use Policy before deploying, it binds on download and bars some uses that are legal\n\n### LBS-27B\n\n1. Serve with `vllm serve inclusionAI/LBS-27B --tensor-parallel-size 4 --max-model-len 65536`, which is what the card's wrapper script runs; keep the context at 32,768 or more for multi-turn images\n2. Build the system prompt with `build_system_prompt` from the LBS branch's `zoomin_grounding_protocol.py`, send the screenshot after `image_path: \u003cname\u003e`, and don't pass `tools`; the model answers in plain text\n3. Parse `\u003caction\u003ecrop_image(image_path=..., x1=..., y1=..., x2=..., y2=...)\u003c/action\u003e`, cut the crop yourself and return it with its mapping to the original image; allow at most two crops per turn and three per episode\n4. Read the final answer as `[x.xx,y.yy]` on a 0 to 1000 scale of the original image, and use your own executor to click\n5. Pass `reasoning_effort` as `xhigh`, `medium` or `low` only, since the template raises an error for `high`, and don't count on `thinking_budget`, which the template ignores\n6. Don't turn on MTP speculative decoding; the MTP weights aren't in the repository though config.json names one MTP layer\n\n## Questions\n\n### Which is better for AI agents, Inkling or LBS-27B?\n\nInkling scores 64.2 (B) on agent readiness against LBS-27B's 53.9 (D), and leads in 3 of 4 scored categories. LBS-27B leads on reach.\n\n\n## For agents\n\n- This comparison as JSON: https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.json, and with the fewest tokens: https://www.anchorterminal.com/compare/inkling-vs-lbs-27b.min.md\n- Over MCP at https://www.anchorterminal.com/mcp (no key): `compare_tools {\"a\": \"inkling\", \"b\": \"lbs-27b\"}`. From a terminal: `anchor compare inkling lbs-27b`\n- Each listing in full: https://www.anchorterminal.com/api/v1/tools/inkling.json and https://www.anchorterminal.com/api/v1/tools/lbs-27b.json\n\n## Other comparisons with Inkling or LBS-27B\n\n- [Agents-A1-4B vs Inkling](https://www.anchorterminal.com/compare/agents-a1-4b-vs-inkling.md)\n- [Agents-A1-4B vs LBS-27B](https://www.anchorterminal.com/compare/agents-a1-4b-vs-lbs-27b.md)\n- [Apertus v1.5 8B vs Inkling](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-inkling.md)\n- [Apertus v1.5 8B vs LBS-27B](https://www.anchorterminal.com/compare/apertus-v1-5-8b-vs-lbs-27b.md)\n- [Apodex-1.1-mini vs Inkling](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-inkling.md)\n- [Apodex-1.1-mini vs LBS-27B](https://www.anchorterminal.com/compare/apodex-1-1-mini-vs-lbs-27b.md)\n- [BigBang-v1 vs Inkling](https://www.anchorterminal.com/compare/bigbang-v1-vs-inkling.md)\n- [BigBang-v1 vs LBS-27B](https://www.anchorterminal.com/compare/bigbang-v1-vs-lbs-27b.md)\n- [Carbon-X vs Inkling](https://www.anchorterminal.com/compare/carbon-x-vs-inkling.md)\n- [Carbon-X vs LBS-27B](https://www.anchorterminal.com/compare/carbon-x-vs-lbs-27b.md)\n- [Cosmos-Reason2-2B vs Inkling](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-inkling.md)\n- [Cosmos-Reason2-2B vs LBS-27B](https://www.anchorterminal.com/compare/cosmos-reason2-2b-vs-lbs-27b.md)\n- [Darwin-36B-Opus vs Inkling](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-inkling.md)\n- [Darwin-36B-Opus vs LBS-27B](https://www.anchorterminal.com/compare/darwin-36b-opus-vs-lbs-27b.md)\n- [DeepSeek-V3.2 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-inkling.md)\n- [DeepSeek-V3.2 vs LBS-27B](https://www.anchorterminal.com/compare/deepseek-v3-2-vs-lbs-27b.md)\n- [DeepSeek V4.1 Flash vs Inkling](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-inkling.md)\n- [DeepSeek V4.1 Flash vs LBS-27B](https://www.anchorterminal.com/compare/deepseek-v4-1-flash-vs-lbs-27b.md)\n- [DeepSeek-V4-Flash-0731 vs Inkling](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-inkling.md)\n- [DeepSeek-V4-Flash-0731 vs LBS-27B](https://www.anchorterminal.com/compare/deepseek-v4-flash-0731-vs-lbs-27b.md)\n- [DiffusionGemma 26B A4B IT vs Inkling](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-inkling.md)\n- [DiffusionGemma 26B A4B IT vs LBS-27B](https://www.anchorterminal.com/compare/diffusiongemma-26b-a4b-it-vs-lbs-27b.md)\n- [Gemma 4 12B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-inkling.md)\n- [Gemma 4 12B IT vs LBS-27B](https://www.anchorterminal.com/compare/gemma-4-12b-it-vs-lbs-27b.md)\n- [Gemma 4 26B A4B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-inkling.md)\n- [Gemma 4 26B A4B IT vs LBS-27B](https://www.anchorterminal.com/compare/gemma-4-26b-a4b-it-vs-lbs-27b.md)\n- [Gemma 4 31B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-inkling.md)\n- [Gemma 4 31B IT vs LBS-27B](https://www.anchorterminal.com/compare/gemma-4-31b-it-vs-lbs-27b.md)\n- [Gemma 4 E2B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-inkling.md)\n- [Gemma 4 E2B IT vs LBS-27B](https://www.anchorterminal.com/compare/gemma-4-e2b-it-vs-lbs-27b.md)\n- [Gemma 4 E4B IT vs Inkling](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-inkling.md)\n- [Gemma 4 E4B IT vs LBS-27B](https://www.anchorterminal.com/compare/gemma-4-e4b-it-vs-lbs-27b.md)\n- [GLM-4.5-Air vs Inkling](https://www.anchorterminal.com/compare/glm-4-5-air-vs-inkling.md)\n- [GLM-4.5-Air vs LBS-27B](https://www.anchorterminal.com/compare/glm-4-5-air-vs-lbs-27b.md)\n- [GLM-4.7-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-inkling.md)\n- [GLM-4.7-Flash vs LBS-27B](https://www.anchorterminal.com/compare/glm-4-7-flash-vs-lbs-27b.md)\n- [GLM-5.3-Flash vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-inkling.md)\n- [GLM-5.3-Flash vs LBS-27B](https://www.anchorterminal.com/compare/glm-5-3-flash-vs-lbs-27b.md)\n- [GLM-5.3 vs Inkling](https://www.anchorterminal.com/compare/glm-5-3-vs-inkling.md)\n- [GLM-5.3 vs LBS-27B](https://www.anchorterminal.com/compare/glm-5-3-vs-lbs-27b.md)\n- [gpt-oss-120b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-inkling.md)\n- [gpt-oss-120b vs LBS-27B](https://www.anchorterminal.com/compare/gpt-oss-120b-vs-lbs-27b.md)\n- [gpt-oss-20b vs Inkling](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-inkling.md)\n- [gpt-oss-20b vs LBS-27B](https://www.anchorterminal.com/compare/gpt-oss-20b-vs-lbs-27b.md)\n- [Granite 4.2 3B vs Inkling](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-inkling.md)\n- [Granite 4.2 3B vs LBS-27B](https://www.anchorterminal.com/compare/granite-4-2-3b-vs-lbs-27b.md)\n- [Hy3 vs Inkling](https://www.anchorterminal.com/compare/hy3-vs-inkling.md)\n- [Hy3 vs LBS-27B](https://www.anchorterminal.com/compare/hy3-vs-lbs-27b.md)\n- [Inkling-Small vs LBS-27B](https://www.anchorterminal.com/compare/inkling-small-vs-lbs-27b.md)\n- [Inkling vs Inkling-Small](https://www.anchorterminal.com/compare/inkling-vs-inkling-small.md)\n- [Inkling vs InternVL3.5-GPT-OSS-20B-A4B-Preview](https://www.anchorterminal.com/compare/inkling-vs-internvl3-5-gpt-oss-20b-a4b-preview.md)\n- [Inkling vs Kimi K3](https://www.anchorterminal.com/compare/inkling-vs-kimi-k3.md)\n- [Inkling vs Kolibri-1](https://www.anchorterminal.com/compare/inkling-vs-kolibri-1.md)\n- [Inkling vs Kronos](https://www.anchorterminal.com/compare/inkling-vs-kronos.md)\n- [Inkling vs Laguna M.1](https://www.anchorterminal.com/compare/inkling-vs-laguna-m-1.md)\n- [Inkling vs Laguna S 2.1](https://www.anchorterminal.com/compare/inkling-vs-laguna-s-2-1.md)\n- [Inkling vs Laguna XS 2.1](https://www.anchorterminal.com/compare/inkling-vs-laguna-xs-2-1.md)\n- [Inkling vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/inkling-vs-lfm2-5-2-6b.md)\n- [Inkling vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/inkling-vs-ling-3-0-tiny.md)\n- [Inkling vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/inkling-vs-mimo-v2-6-distill-qwen-9b.md)\n- [Inkling vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/inkling-vs-minicpm-o-4-5.md)\n- [Inkling vs MiniCPM5-2B](https://www.anchorterminal.com/compare/inkling-vs-minicpm5-2b.md)\n- [Inkling vs MiniMax-M2.5](https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-5.md)\n- [Inkling vs MiniMax-M2.7](https://www.anchorterminal.com/compare/inkling-vs-minimax-m2-7.md)\n- [Inkling vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/inkling-vs-minimax-m3-1-flash.md)\n- [Inkling vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/inkling-vs-muse-glimmer-30b.md)\n- [Inkling vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/inkling-vs-nanbeige-4-3-33b.md)\n- [Inkling vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [Inkling vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [Inkling vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-30b-a3b.md)\n- [Inkling vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-4b.md)\n- [Inkling vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [Inkling vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-super-120b-a12b.md)\n- [Inkling vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/inkling-vs-nemotron-3-ultra-550b-a55b.md)\n- [Inkling vs occamy-1.0](https://www.anchorterminal.com/compare/inkling-vs-occamy-1-0.md)\n- [Inkling vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/inkling-vs-olmo-3-7b-think.md)\n- [Inkling vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-35b-a3b.md)\n- [Inkling vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-397b.md)\n- [Inkling vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/inkling-vs-ornith-1-5-9b.md)\n- [Inkling vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-vs-qwen3-30b-a3b-instruct-2507.md)\n- [Inkling vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/inkling-vs-qwen3-4b-instruct-2507.md)\n- [Inkling vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-0-8b.md)\n- [Inkling vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-122b-a10b.md)\n- [Inkling vs Qwen3.5-2B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-2b.md)\n- [Inkling vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-397b-a17b.md)\n- [Inkling vs Qwen3.5-4B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-4b.md)\n- [Inkling vs Qwen3.5-9B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-5-9b.md)\n- [Inkling vs Qwen3.6-27B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-27b.md)\n- [Inkling vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-6-35b-a3b.md)\n- [Inkling vs Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-27b.md)\n- [Inkling vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-vs-qwen3-8-flash-next.md)\n- [Inkling vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-30b-a3b-instruct.md)\n- [Inkling vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/inkling-vs-qwen3-coder-next.md)\n- [Inkling vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-omni-30b-a3b-instruct.md)\n- [Inkling vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-2b-instruct.md)\n- [Inkling vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-30b-a3b-instruct.md)\n- [Inkling vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-32b-instruct.md)\n- [Inkling vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-4b-instruct.md)\n- [Inkling vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/inkling-vs-qwen3-vl-8b-instruct.md)\n- [Inkling vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/inkling-vs-qwopus3-8-27b-flash-v2.md)\n- [Inkling vs Recursive Flint](https://www.anchorterminal.com/compare/inkling-vs-recursive-flint.md)\n- [Inkling vs SmolLM3-3B](https://www.anchorterminal.com/compare/inkling-vs-smollm3-3b.md)\n- [Inkling vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/inkling-vs-spark-x2-6-4b.md)\n- [Inkling vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-27b.md)\n- [Inkling vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/inkling-vs-swift-1-5-qwen3-8-flash-next.md)\n- [Inkling vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/inkling-vs-thinkingcap-qwen3-8-27b.md)\n- [Inkling vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/inkling-vs-unlimited-ocr-2.md)\n- [InternVL3.5-GPT-OSS-20B-A4B-Preview vs LBS-27B](https://www.anchorterminal.com/compare/internvl3-5-gpt-oss-20b-a4b-preview-vs-lbs-27b.md)\n- [Kimi K3 vs LBS-27B](https://www.anchorterminal.com/compare/kimi-k3-vs-lbs-27b.md)\n- [Kolibri-1 vs LBS-27B](https://www.anchorterminal.com/compare/kolibri-1-vs-lbs-27b.md)\n- [Kronos vs LBS-27B](https://www.anchorterminal.com/compare/kronos-vs-lbs-27b.md)\n- [Laguna M.1 vs LBS-27B](https://www.anchorterminal.com/compare/laguna-m-1-vs-lbs-27b.md)\n- [Laguna S 2.1 vs LBS-27B](https://www.anchorterminal.com/compare/laguna-s-2-1-vs-lbs-27b.md)\n- [Laguna XS 2.1 vs LBS-27B](https://www.anchorterminal.com/compare/laguna-xs-2-1-vs-lbs-27b.md)\n- [LBS-27B vs LFM2.5-2.6B](https://www.anchorterminal.com/compare/lbs-27b-vs-lfm2-5-2-6b.md)\n- [LBS-27B vs Ling-3.0-tiny](https://www.anchorterminal.com/compare/lbs-27b-vs-ling-3-0-tiny.md)\n- [LBS-27B vs MiMo-V2.6 Distill Qwen 9B](https://www.anchorterminal.com/compare/lbs-27b-vs-mimo-v2-6-distill-qwen-9b.md)\n- [LBS-27B vs MiniCPM-o 4.5](https://www.anchorterminal.com/compare/lbs-27b-vs-minicpm-o-4-5.md)\n- [LBS-27B vs MiniCPM5-2B](https://www.anchorterminal.com/compare/lbs-27b-vs-minicpm5-2b.md)\n- [LBS-27B vs MiniMax-M2.5](https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m2-5.md)\n- [LBS-27B vs MiniMax-M2.7](https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m2-7.md)\n- [LBS-27B vs MiniMax-M3.1-Flash](https://www.anchorterminal.com/compare/lbs-27b-vs-minimax-m3-1-flash.md)\n- [LBS-27B vs Muse Glimmer 30B](https://www.anchorterminal.com/compare/lbs-27b-vs-muse-glimmer-30b.md)\n- [LBS-27B vs Nanbeige4.3-33B](https://www.anchorterminal.com/compare/lbs-27b-vs-nanbeige-4-3-33b.md)\n- [LBS-27B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-5-bolt-e4b-4gb.md)\n- [LBS-27B vs Nemotron 3.5 Lightning 30B A3B](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-5-lightning-30b-a3b.md)\n- [LBS-27B vs Nemotron 3 Nano 30B A3B](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-30b-a3b.md)\n- [LBS-27B vs Nemotron 3 Nano 4B](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-4b.md)\n- [LBS-27B vs Nemotron 3 Nano Omni 30B A3B Reasoning](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-nano-omni-30b-a3b-reasoning.md)\n- [LBS-27B vs Nemotron 3 Super 120B A12B](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-super-120b-a12b.md)\n- [LBS-27B vs Nemotron 3 Ultra 550B A55B](https://www.anchorterminal.com/compare/lbs-27b-vs-nemotron-3-ultra-550b-a55b.md)\n- [LBS-27B vs occamy-1.0](https://www.anchorterminal.com/compare/lbs-27b-vs-occamy-1-0.md)\n- [LBS-27B vs Olmo 3 7B Think](https://www.anchorterminal.com/compare/lbs-27b-vs-olmo-3-7b-think.md)\n- [LBS-27B vs Ornith-1.5-35B-A3B](https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-35b-a3b.md)\n- [LBS-27B vs Ornith-1.5-397B](https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-397b.md)\n- [LBS-27B vs Ornith-1.5-9B](https://www.anchorterminal.com/compare/lbs-27b-vs-ornith-1-5-9b.md)\n- [LBS-27B vs Qwen3-30B-A3B-Instruct-2507](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-30b-a3b-instruct-2507.md)\n- [LBS-27B vs Qwen3-4B-Instruct-2507](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-4b-instruct-2507.md)\n- [LBS-27B vs Qwen3.5-0.8B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-0-8b.md)\n- [LBS-27B vs Qwen3.5-122B-A10B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-122b-a10b.md)\n- [LBS-27B vs Qwen3.5-2B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-2b.md)\n- [LBS-27B vs Qwen3.5-397B-A17B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-397b-a17b.md)\n- [LBS-27B vs Qwen3.5-4B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-4b.md)\n- [LBS-27B vs Qwen3.5-9B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-5-9b.md)\n- [LBS-27B vs Qwen3.6-27B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-6-27b.md)\n- [LBS-27B vs Qwen3.6-35B-A3B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-6-35b-a3b.md)\n- [LBS-27B vs Qwen3.8-27B](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-8-27b.md)\n- [LBS-27B vs Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-8-flash-next.md)\n- [LBS-27B vs Qwen3-Coder-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-coder-30b-a3b-instruct.md)\n- [LBS-27B vs Qwen3-Coder-Next](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-coder-next.md)\n- [LBS-27B vs Qwen3-Omni-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-omni-30b-a3b-instruct.md)\n- [LBS-27B vs Qwen3-VL-2B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-2b-instruct.md)\n- [LBS-27B vs Qwen3-VL-30B-A3B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-30b-a3b-instruct.md)\n- [LBS-27B vs Qwen3-VL-32B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-32b-instruct.md)\n- [LBS-27B vs Qwen3-VL-4B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-4b-instruct.md)\n- [LBS-27B vs Qwen3-VL-8B-Instruct](https://www.anchorterminal.com/compare/lbs-27b-vs-qwen3-vl-8b-instruct.md)\n- [LBS-27B vs Qwopus3.8-27B-Flash-V2](https://www.anchorterminal.com/compare/lbs-27b-vs-qwopus3-8-27b-flash-v2.md)\n- [LBS-27B vs Recursive Flint](https://www.anchorterminal.com/compare/lbs-27b-vs-recursive-flint.md)\n- [LBS-27B vs SmolLM3-3B](https://www.anchorterminal.com/compare/lbs-27b-vs-smollm3-3b.md)\n- [LBS-27B vs Spark-X2.6-4B](https://www.anchorterminal.com/compare/lbs-27b-vs-spark-x2-6-4b.md)\n- [LBS-27B vs Swift 1.5 Qwen3.8-27B](https://www.anchorterminal.com/compare/lbs-27b-vs-swift-1-5-qwen3-8-27b.md)\n- [LBS-27B vs Swift 1.5 Qwen3.8-Flash-Next](https://www.anchorterminal.com/compare/lbs-27b-vs-swift-1-5-qwen3-8-flash-next.md)\n- [LBS-27B vs ThinkingCap (Qwen3.8 27B)](https://www.anchorterminal.com/compare/lbs-27b-vs-thinkingcap-qwen3-8-27b.md)\n- [LBS-27B vs Baidu Unlimited-OCR-2](https://www.anchorterminal.com/compare/lbs-27b-vs-unlimited-ocr-2.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": "2026-10-27", "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": "Inkling vs LBS-27B", "url": "" } ], "description": "Inkling scores 64.2 (B) to LBS-27B's 53.9 (D) for open-weight models you run yourself. Prices, MCP, x402, uptime and agent notes side by side.", "facts": [ "Inkling B 64.2", "LBS-27B D 53.9", "scores" ], "h1": "Inkling vs LBS-27B", "image": "https://www.anchorterminal.com/assets/og/compare-inkling-vs-lbs-27b.png", "path": "/compare/inkling-vs-lbs-27b", "published": "2026-10-01", "section": "tools", "title": "Inkling vs LBS-27B for AI agents in 2026: scores and prices", "toc": null, "updated": "2026-10-27", "url": "https://www.anchorterminal.com/compare/inkling-vs-lbs-27b" }, "tokens": { "markdown": 6100, "slim": 480 }, "version": 1 }