Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 8B vs LBS-27B
Granite 4.2 8B scores 61 (C) on agent readiness against LBS-27B's 55.8 (C), and leads in every scored category. Both do open-weight models you run yourself.
Best open-weight models you download and run yourself for AI agents · All 4969 open weights comparisons
Which one, for what
Best for Agents that want a documented, signed, Apache 2.0 reasoning model with tool calling on a 16 GB machine
Ahead on
- Reach, 95 against 60
- Risk, 55 against 50
- Agent interface, 85 against 70
- Documentation and upkeep, 92 against 43
Watch for
No safety results published for it
LBS-27B C
Best 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.
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
No independent benchmark result yet; ScreenSpot-Pro, OS-World-G, PerceptionBench and HR-Bench numbers are inclusionAI's own runs
Why the edge
Each category where one leads by five points or more, with the reason behind each side's score from its assessment. The numbers are in the table below; this is what they stand for.
Documentation and upkeep Granite 4.2 8B +49
Granite 4.2 8B 92
Model card 17, Intended use (best for), limitations (ethical considerations and limitations), architecture, parameters (8B), context length (128K native) and 12 tested languages are on the card. Training data 20, IBM's disclosure file for the 8B lists the datasets used in pre-training and post-training as machine-readable metadata, and the card describes the three training stages. Last change 20, the last commit, on 20 October 2026, replaced model.safetensors.index.json (titled "granite-4.2 index file fix"), 21 days before this check. Responsiveness 20, Of the 5 discussions that aren't pull requests (13 September to 5 November 2026), 4 have a reply from an ibm-granite member. Version policy 5, Granite 4.1 8B stays in its own repository and 4.2 came out in new ones. File health 10, Config, template and card agree on the architecture, the 131,072-token context and the thinking switch. 17 + 20 + 20 + 20 + 5 + 10 = 92.
LBS-27B 43
The model card earns 8, with intended use, one limitation and parameters, and no architecture, context, languages or cut-off. Training data earns 5 for a general description of synthetic GUI data with no cut-off. Last change earns 20 for 26 October 2026. Responsiveness earns 0, the one discussion unanswered. Version policy earns 5 for a first release. File health earns 5, as the config still sets an MTP layer the weights lack and the card names a reasoning setting the template refuses.
Reach Granite 4.2 8B +35
Granite 4.2 8B 95
Memory 30, IBM's own 4-bit MLX build granite-4.2-8b-q4-mlx is 4.95 GB, and 4.95 GB × 1.2 = 5.9 GB, within 8 GB. Its Q4_0 GGUF is 5.06 GB and Ollama's library build granite4.2:8b (5.3 GB) fits 8 GB too. Runtimes 25, Released versions run the granite architecture in llama.cpp (granite, b12242), vLLM (GraniteForCausalLM in the v0.33.0 registry), SGLang (granite.py at v0.5.23), Transformers (v5.22.2) and Ollama (its own granite4.2 library entry, 8b tag). Builds 15, IBM publishes FP8, MXFP4 and NVFP4 safetensors builds, a GGUF repository with Q4_0 to Q8_0 and BF16 files, and 4-bit, 8-bit and BF16 MLX builds, so quantised builds at two precisions or more. Terms 15, Apache 2.0, an OSI-approved licence, with no use policy or other terms added on the card. Download 10, the Hub API reports gated false for the BF16, FP8, MXFP4, NVFP4, GGUF and MLX repositories, so the files download with no account and nothing to accept. Hosted 0, Hugging Face maps one inference provider (DeepInfra, live), short of the two the line needs. 30 + 25 + 15 + 15 + 10 + 0 = 95.
LBS-27B 60
Memory earns 10, since the only build is 54.73 GB of BF16, about 66 GB with a fifth added, which fits the reference machine but not 64 GB. Runtimes earn 25 from released vLLM, SGLang, Transformers and llama.cpp, which all carry Qwen3.8-27B's architecture, and Ollama through the llama.cpp release it pins, so 25. Builds earn 0, as inclusionAI publishes no quantised build and the GGUF copies are bartowski's and mradermacher's. Terms earn 15 for Apache 2.0 with nothing added, on the weights and on the base. Download earns 10, with no gate. Hosted earns 0, as no provider or inclusionAI API serves it.
Agent interface Granite 4.2 8B +15
Granite 4.2 8B 85
Chat template 20, chat_template.jinja in the repository, with roles, tools, tool responses, the thinking switch and low effort. Tool-calling format 25, the card has tool-calling sections for vLLM and SGLang, declares tools with OpenAI's function schema and names the parser to use, qwen3_coder, which both runtimes ship in the released versions read. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so it renders several calls in one turn, and the card names tool calling and agentic workflows as what it's best for. Structured output 0, the card doesn't document JSON or JSON Schema output or how to ask for it. Reasoning control 10, the card documents thinking on by default, non-thinking and low-effort modes per request through the template (enable_thinking and low_effort), with the reasoning returned apart from the answer. Context 10, 131,072 tokens natively per the card and config.json. 20 + 25 + 20 + 0 + 10 + 10 = 85.
LBS-27B 70
The chat template earns 20, Qwen's Jinja file in the repository. The tool-calling format earns 10, as general tool calls rest on the inherited template and the crop action is parsed by inclusionAI's own code, not a runtime parser. Trained tool calling earns 20 for up to two crop actions per turn learned in GRPO. Structured output earns 0. Reasoning control earns 10, with reasoning effort documented and the reasoning shown as think text. Context earns 10 for 262,144 tokens with no scaling.
Risk Granite 4.2 8B +5
Granite 4.2 8B 55
File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, the files sit in the ibm-granite organisation, which IBM's Granite docs and the GitHub README link to (10). Safety evaluation 0, no safety results on the card. Agent guidance 5, General cautions. Licence risk 15, Apache 2.0 has no use policy, field-of-use limit, threshold or change clause, and the card's licence link resolves. Security programme 5, www.ibm.com/.well-known/security.txt names IBM PSIRT, read for the 3B listing on 4 November 2026 (5). 15 + 15 + 0 + 5 + 15 + 5 = 55.
LBS-27B 50
File safety earns 15, safetensors only but with the documented route running the publisher's scripts to serve it and to write its system prompt. Provenance earns 15, inclusionAI's own organisation with a hash for every file. Safety evaluation and agent guidance earn 0, as nothing is published on either, prompt injection through screenshots included. Licence risk keeps all 15 under Apache 2.0. The security programme earns 5 for Ant Group's AntSRC, which isn't linked to the model.
Score by category
| Category | Weight this run | Granite 4.2 8B | LBS-27B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 60 | Granite 4.2 8B +35 |
| Risk | 20%20 | 55 | 50 | Granite 4.2 8B +5 |
| Agent interface | 10%10 | 85 | 70 | Granite 4.2 8B +15 |
| Documentation and upkeep | 10%10 | 92 | 43 | Granite 4.2 8B +49 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | C 55.8/100 |
Facts side by side
| Fact | Granite 4.2 8B | LBS-27B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | inclusionAI (Ant Group) |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| 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) |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-20 | 2026-10-26 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
How the scores have moved
Granite 4.2 8B
No score change since it was listed.
Verdicts
Granite 4.2 8B
IBM's mid-size reasoning cousin, with the same strengths as the 3B. It runs in every runtime we count from IBM's own builds on a 16 GB machine, is signed, plain Apache 2.0, and comes with a disclosure of its training data. No safety results are published and structured output isn't documented.
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.
Before you call either
Granite 4.2 8B
- Start it with
ollama run granite4.2:8b, orllama-server -hf ibm-granite/granite-4.2-8b-GGUF:Q4_K_M --jinja - With vLLM 0.32.0 or later leave out
--reasoning-parser-plugin, since the parser is built in, and use--tool-call-parser qwen3_coder - Thinking is on by default. Pass
enable_thinkingfalse to turn it off orlow_efforttrue for short reasoning - The context is 131,072 tokens. The card's 512K extension isn't documented
- Validate JSON output yourself, since structured output isn't documented
- IBM recommends Granite Guardian beside it to flag risky inputs and outputs
LBS-27B
- 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_promptfrom the LBS branch'szoomin_grounding_protocol.py, send the screenshot afterimage_path: <name>, and don't passtools; the model answers in plain text - Parse
<action>crop_image(image_path=..., x1=..., y1=..., x2=..., y2=...)</action>, 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_effortasxhigh,mediumorlowonly, since the template raises an error forhigh, and don't count onthinking_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
Questions
Which is better for AI agents, Granite 4.2 8B or LBS-27B?
Granite 4.2 8B scores 61 (C) on agent readiness against LBS-27B's 55.8 (C), and leads in every scored category.
Other comparisons with Granite 4.2 8B or LBS-27B
- Agents-A1-4B vs Granite 4.2 8B
- Agents-A1-4B vs LBS-27B
- Apertus v1.5 8B vs Granite 4.2 8B
- Apertus v1.5 8B vs LBS-27B
- Apodex-1.1-mini vs Granite 4.2 8B
- Apodex-1.1-mini vs LBS-27B
- Arete-27B vs Granite 4.2 8B
- Arete-27B vs LBS-27B
- BigBang-v1 vs Granite 4.2 8B
- BigBang-v1 vs LBS-27B
- Carbon-X vs Granite 4.2 8B
- Carbon-X vs LBS-27B
- Cosmos-Reason2-2B vs Granite 4.2 8B
- Cosmos-Reason2-2B vs LBS-27B
- Darwin-36B-Opus vs Granite 4.2 8B
- Darwin-36B-Opus vs LBS-27B
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs LBS-27B
- DeepSeek V4.1 Flash vs Granite 4.2 8B
- DeepSeek V4.1 Flash vs LBS-27B
- DeepSeek-V4-Flash-0731 vs Granite 4.2 8B
- DeepSeek-V4-Flash-0731 vs LBS-27B
- DiffusionGemma 26B A4B IT vs Granite 4.2 8B
- DiffusionGemma 26B A4B IT vs LBS-27B
- Gemma 4 12B IT vs Granite 4.2 8B
- Gemma 4 12B IT vs LBS-27B
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs LBS-27B
- Gemma 4 31B IT vs Granite 4.2 8B
- Gemma 4 31B IT vs LBS-27B
- Gemma 4 E2B IT vs Granite 4.2 8B
- Gemma 4 E2B IT vs LBS-27B
- Gemma 4 E4B IT vs Granite 4.2 8B
- Gemma 4 E4B IT vs LBS-27B
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs LBS-27B
- GLM-4.7-Flash vs Granite 4.2 8B
- GLM-4.7-Flash vs LBS-27B
- GLM-5.3-Flash vs Granite 4.2 8B
- GLM-5.3-Flash vs LBS-27B
- GLM-5.3 vs Granite 4.2 8B
- GLM-5.3 vs LBS-27B
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs LBS-27B
- gpt-oss-20b vs Granite 4.2 8B
- gpt-oss-20b vs LBS-27B
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs LBS-27B
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs LBS-27B
- Granite 4.2 8B vs Hy-Memory-30B-A3B
- Granite 4.2 8B vs Hy3
- Granite 4.2 8B vs Inkling
- Granite 4.2 8B vs Inkling-Small
- Granite 4.2 8B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Granite 4.2 8B vs Kimi K3
- Granite 4.2 8B vs Kimi K3.1 Pro
- Granite 4.2 8B vs Kolibri-1
- Granite 4.2 8B vs Kronos
- Granite 4.2 8B vs Laguna M.1
- Granite 4.2 8B vs Laguna S 2.1
- Granite 4.2 8B vs Laguna XS 2.1
- Granite 4.2 8B vs LFM2.5-2.6B
- Granite 4.2 8B vs LFM3-1.7B
- Granite 4.2 8B vs LFM3-Audio-2B
- Granite 4.2 8B vs LFM3-Omni-2B
- Granite 4.2 8B vs LFM3-VL-2B
- Granite 4.2 8B vs Ling-3.0-tiny
- Granite 4.2 8B vs Ling-3.1-flash-1019
- Granite 4.2 8B vs MiMo-V2.6 Distill Qwen 9B
- Granite 4.2 8B vs MiniCPM-o 4.5
- Granite 4.2 8B vs MiniCPM-V 4.7 1B
- Granite 4.2 8B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 8B vs MiniCPM5-2B
- Granite 4.2 8B vs MiniMax-M2.5
- Granite 4.2 8B vs MiniMax-M2.7
- Granite 4.2 8B vs MiniMax-M3.1-Flash
- Granite 4.2 8B vs Mistral Large 4
- Granite 4.2 8B vs Muse Glimmer 30B
- Granite 4.2 8B vs Nanbeige4.3-33B
- Granite 4.2 8B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Granite 4.2 8B vs Nemotron 3.5 Lightning 30B A3B
- Granite 4.2 8B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 8B vs Nemotron 3 Nano 4B
- Granite 4.2 8B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Granite 4.2 8B vs Nemotron 3 Super 120B A12B
- Granite 4.2 8B vs Nemotron 3 Ultra 550B A55B
- Granite 4.2 8B vs occamy-1.0
- Granite 4.2 8B vs Olmo 3 7B Think
- Granite 4.2 8B vs Ornith-1.5-122B
- Granite 4.2 8B vs Ornith-1.5-35B-A3B
- Granite 4.2 8B vs Ornith-1.5-397B
- Granite 4.2 8B vs Ornith-1.5-9B
- Granite 4.2 8B vs Qwen-AgentWorld-35B-A3B
- Granite 4.2 8B vs Qwen3-30B-A3B-Instruct-2507
- Granite 4.2 8B vs Qwen3-4B-Instruct-2507
- Granite 4.2 8B vs Qwen3.5-0.8B
- Granite 4.2 8B vs Qwen3.5-122B-A10B
- Granite 4.2 8B vs Qwen3.5-2B
- Granite 4.2 8B vs Qwen3.5-397B-A17B
- Granite 4.2 8B vs Qwen3.5-4B
- Granite 4.2 8B vs Qwen3.5-9B
- Granite 4.2 8B vs Qwen3.6-27B
- Granite 4.2 8B vs Qwen3.6-35B-A3B
- Granite 4.2 8B vs Qwen3.8-27B
- Granite 4.2 8B vs Qwen3.8-Flash-Next
- Granite 4.2 8B vs Qwen3-Coder-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-Coder-Next
- Granite 4.2 8B vs Qwen3-Omni-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-VL-2B-Instruct
- Granite 4.2 8B vs Qwen3-VL-30B-A3B-Instruct
- Granite 4.2 8B vs Qwen3-VL-32B-Instruct
- Granite 4.2 8B vs Qwen3-VL-4B-Instruct
- Granite 4.2 8B vs Qwen3-VL-8B-Instruct
- Granite 4.2 8B vs Qwopus3.8-27B-Flash-V2
- Granite 4.2 8B vs Recursive Flint
- Granite 4.2 8B vs Ripple-65B Preview
- Granite 4.2 8B vs SmolLM3-3B
- Granite 4.2 8B vs Spark-X2.6-4B
- Granite 4.2 8B vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 8B vs Swift 1.5 Qwen3.8-Flash-Next
- Granite 4.2 8B vs ThinkingCap (Qwen3.8 27B)
- Granite 4.2 8B vs Baidu Unlimited-OCR-2
- Hy-Memory-30B-A3B vs LBS-27B
- Hy3 vs LBS-27B
- Inkling-Small vs LBS-27B
- Inkling vs LBS-27B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs LBS-27B
- Kimi K3.1 Pro vs LBS-27B
- Kimi K3 vs LBS-27B
- Kolibri-1 vs LBS-27B
- Kronos vs LBS-27B
- Laguna M.1 vs LBS-27B
- Laguna S 2.1 vs LBS-27B
- Laguna XS 2.1 vs LBS-27B
- LBS-27B vs LFM2.5-2.6B
- LBS-27B vs LFM3-1.7B
- LBS-27B vs LFM3-Audio-2B
- LBS-27B vs LFM3-Omni-2B
- LBS-27B vs LFM3-VL-2B
- LBS-27B vs Ling-3.0-tiny
- LBS-27B vs Ling-3.1-flash-1019
- LBS-27B vs MiMo-V2.6 Distill Qwen 9B
- LBS-27B vs MiniCPM-o 4.5
- LBS-27B vs MiniCPM-V 4.7 1B
- LBS-27B vs MiniCPM-V 4.7 35B-A3B
- LBS-27B vs MiniCPM5-2B
- LBS-27B vs MiniMax-M2.5
- LBS-27B vs MiniMax-M2.7
- LBS-27B vs MiniMax-M3.1-Flash
- LBS-27B vs Mistral Large 4
- LBS-27B vs Muse Glimmer 30B
- LBS-27B vs Nanbeige4.3-33B
- LBS-27B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- LBS-27B vs Nemotron 3.5 Lightning 30B A3B
- LBS-27B vs Nemotron 3 Nano 30B A3B
- LBS-27B vs Nemotron 3 Nano 4B
- LBS-27B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- LBS-27B vs Nemotron 3 Super 120B A12B
- LBS-27B vs Nemotron 3 Ultra 550B A55B
- LBS-27B vs occamy-1.0
- LBS-27B vs Olmo 3 7B Think
- LBS-27B vs Ornith-1.5-122B
- LBS-27B vs Ornith-1.5-35B-A3B
- LBS-27B vs Ornith-1.5-397B
- LBS-27B vs Ornith-1.5-9B
- LBS-27B vs Qwen-AgentWorld-35B-A3B
- LBS-27B vs Qwen3-30B-A3B-Instruct-2507
- LBS-27B vs Qwen3-4B-Instruct-2507
- LBS-27B vs Qwen3.5-0.8B
- LBS-27B vs Qwen3.5-122B-A10B
- LBS-27B vs Qwen3.5-2B
- LBS-27B vs Qwen3.5-397B-A17B
- LBS-27B vs Qwen3.5-4B
- LBS-27B vs Qwen3.5-9B
- LBS-27B vs Qwen3.6-27B
- LBS-27B vs Qwen3.6-35B-A3B
- LBS-27B vs Qwen3.8-27B
- LBS-27B vs Qwen3.8-Flash-Next
- LBS-27B vs Qwen3-Coder-30B-A3B-Instruct
- LBS-27B vs Qwen3-Coder-Next
- LBS-27B vs Qwen3-Omni-30B-A3B-Instruct
- LBS-27B vs Qwen3-VL-2B-Instruct
- LBS-27B vs Qwen3-VL-30B-A3B-Instruct
- LBS-27B vs Qwen3-VL-32B-Instruct
- LBS-27B vs Qwen3-VL-4B-Instruct
- LBS-27B vs Qwen3-VL-8B-Instruct
- LBS-27B vs Qwopus3.8-27B-Flash-V2
- LBS-27B vs Recursive Flint
- LBS-27B vs Ripple-65B Preview
- LBS-27B vs SmolLM3-3B
- LBS-27B vs Spark-X2.6-4B
- LBS-27B vs Swift 1.5 Qwen3.8-27B
- LBS-27B vs Swift 1.5 Qwen3.8-Flash-Next
- LBS-27B vs ThinkingCap (Qwen3.8 27B)
- LBS-27B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-8b-vs-lbs-27b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-4-2-8b.json·/api/v1/tools/lbs-27b.json - From a terminal
anchor compare granite-4-2-8b lbs-27b(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-8b", "b": "lbs-27b"}at/mcp, no key