Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 8B vs LFM2.5-2.6B
Granite 4.2 8B scores 61 (C) on agent readiness against LFM2.5-2.6B's 50.3 (D), 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 90
- Risk, 55 against 50
- Agent interface, 85 against 75
- Documentation and upkeep, 92 against 57
Watch for
No safety results published for it
Best for Agents that want a small local helper for tool calls, extraction and RAG on a laptop, phone or CPU, at organisations under the licence's revenue threshold
No category where it leads by five points or more, and no fact that sets it apart.
Watch for
Liquid lists it as deprecated, replaced by LFM3-1.7B; deprecated models stay downloadable but get no further updates
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 +35
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.
LFM2.5-2.6B 57
The model card earns 17, with everything but a knowledge cut-off. Training data earns 5 for a general description without a cut-off. The last change earns 20, a card commit on 3 November 2026 naming LFM3-1.7B as the new version. Responsiveness earns 5, with Liquid replies in 2 of 16 discussions. Version policy earns 5, as Liquid now lists the model as deprecated with a replacement but no date. File health earns 5, since the files agree but a report about the card waits without a reply.
Agent interface Granite 4.2 8B +10
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.
LFM2.5-2.6B 75
The chat template earns 20 for chat_template.jinja in the repository. The tool-calling format earns 25, as Liquid's card and tool-use page say how tools go in and how calls come back, and its vLLM and SGLang pages name the lfm2 parser. Trained tool calling earns 20, with several calls in one Python list and agentic RL inside agent harnesses. Structured output earns nothing, as JSON output isn't documented for the model. Reasoning control earns nothing, since the model always thinks. Context earns 10 for 131,072 tokens trained.
Reach Granite 4.2 8B +5
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.
LFM2.5-2.6B 90
Memory earns the full 30, since Liquid's own 4-bit GGUF is 1.59 GB and fits 8 GB with room to spare. Runtimes earn 25, with the lfm2 architecture in released llama.cpp, vLLM, SGLang and Transformers, and in Ollama through the llama.cpp version it pins. Builds earn 15 for Liquid's own GGUF, MLX and ONNX builds at many precisions. Terms earn 10, a custom licence that is free for commercial use under $10M of annual revenue. Download earns 10, with no gate. Hosted earns nothing, as Hugging Face maps no inference provider and Liquid's docs list no hosted API for it.
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.
LFM2.5-2.6B 50
File safety earns 25, safetensors and GGUF only, and nothing from the repository runs to load it or build prompts. Provenance earns 15, files in the LiquidAI organisation Liquid links to, with a checksum for every file. Safety evaluation and agent guidance earn nothing, since Liquid publishes neither. Licence risk earns 10, losing 5 for the revenue threshold, with no use policy and no change since release. The security programme earns nothing, since no security.txt, disclosure policy or security contact was found.
Score by category
| Category | Weight this run | Granite 4.2 8B | LFM2.5-2.6B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 90 | Granite 4.2 8B +5 |
| Risk | 20%20 | 55 | 50 | Granite 4.2 8B +5 |
| Agent interface | 10%10 | 85 | 75 | Granite 4.2 8B +10 |
| Documentation and upkeep | 10%10 | 92 | 57 | Granite 4.2 8B +35 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 61/100 | D 50.3/100 |
Facts side by side
| Fact | Granite 4.2 8B | LFM2.5-2.6B |
|---|---|---|
| Kind | Open-weight model | Open-weight model |
| Vendor | IBM | Liquid AI |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | ||
| Auth | None | None |
| Pricing | Free | Free |
| x402 | no | no |
| Licence | Apache-2.0 | LFM Open License v1.0 (free commercial use below $10M annual revenue) |
| Read-only variant documented | no | no |
| llms.txt | no | yes |
| Last release | 2026-10-20 | 2026-11-03 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | none | 2.5/5 (4) |
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.
LFM2.5-2.6B
A small, fast model for tool calls, extraction and long-context steps on a laptop or phone, which Liquid now lists as deprecated in favour of LFM3-1.7B. Liquid's own 4-bit build is 1.6 GB and five common runtimes run it. It always thinks, and organisations over $10M of revenue need another licence. There are no safety results or security contact.
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
LFM2.5-2.6B
- Quickest start is
ollama run LiquidAI/lfm2.5-2.6b, 1.7 GB, orllama-cli -hf LiquidAI/LFM2.5-2.6B-GGUF - With vLLM or SGLang pass
--tool-call-parser lfm2; for vLLM add--reasoning-parser qwen3so the thinking comes back separately - Sample at temperature 0.1, top_k 50 and repetition_penalty 1.1, as the card and generation_config.json set
- Put tools in the system prompt as
List of tools: [...]JSON, or pass tools to apply_chat_template; calls come back as a Python list of function calls, and the system prompt can ask for JSON calls instead - Leave max_tokens unset or generous, since a low cap cuts the reasoning off mid-thought
- Earlier thinking is dropped from the prompt unless
preserve_thinkingis true - Liquid's 328M LFM2.5-2.6B-DSpark drafter speeds decoding about 2.6 times in SGLang and on Apple silicon, per Liquid
- Validate JSON output yourself or use the runtime's guided decoding, since structured output isn't documented
Questions
Which is better for AI agents, Granite 4.2 8B or LFM2.5-2.6B?
Granite 4.2 8B scores 61 (C) on agent readiness against LFM2.5-2.6B's 50.3 (D), and leads in every scored category.
Other comparisons with Granite 4.2 8B or LFM2.5-2.6B
- Agents-A1-4B vs Granite 4.2 8B
- Agents-A1-4B vs LFM2.5-2.6B
- Apertus v1.5 8B vs Granite 4.2 8B
- Apertus v1.5 8B vs LFM2.5-2.6B
- Apodex-1.1-mini vs Granite 4.2 8B
- Apodex-1.1-mini vs LFM2.5-2.6B
- Arete-27B vs Granite 4.2 8B
- Arete-27B vs LFM2.5-2.6B
- BigBang-v1 vs Granite 4.2 8B
- BigBang-v1 vs LFM2.5-2.6B
- Carbon-X vs Granite 4.2 8B
- Carbon-X vs LFM2.5-2.6B
- Cosmos-Reason2-2B vs Granite 4.2 8B
- Cosmos-Reason2-2B vs LFM2.5-2.6B
- Darwin-36B-Opus vs Granite 4.2 8B
- Darwin-36B-Opus vs LFM2.5-2.6B
- DeepSeek-V3.2 vs Granite 4.2 8B
- DeepSeek-V3.2 vs LFM2.5-2.6B
- DeepSeek V4.1 Flash vs Granite 4.2 8B
- DeepSeek V4.1 Flash vs LFM2.5-2.6B
- DeepSeek-V4-Flash-0731 vs Granite 4.2 8B
- DeepSeek-V4-Flash-0731 vs LFM2.5-2.6B
- DiffusionGemma 26B A4B IT vs Granite 4.2 8B
- DiffusionGemma 26B A4B IT vs LFM2.5-2.6B
- Gemma 4 12B IT vs Granite 4.2 8B
- Gemma 4 12B IT vs LFM2.5-2.6B
- Gemma 4 26B A4B IT vs Granite 4.2 8B
- Gemma 4 26B A4B IT vs LFM2.5-2.6B
- Gemma 4 31B IT vs Granite 4.2 8B
- Gemma 4 31B IT vs LFM2.5-2.6B
- Gemma 4 E2B IT vs Granite 4.2 8B
- Gemma 4 E2B IT vs LFM2.5-2.6B
- Gemma 4 E4B IT vs Granite 4.2 8B
- Gemma 4 E4B IT vs LFM2.5-2.6B
- GLM-4.5-Air vs Granite 4.2 8B
- GLM-4.5-Air vs LFM2.5-2.6B
- GLM-4.7-Flash vs Granite 4.2 8B
- GLM-4.7-Flash vs LFM2.5-2.6B
- GLM-5.3-Flash vs Granite 4.2 8B
- GLM-5.3-Flash vs LFM2.5-2.6B
- GLM-5.3 vs Granite 4.2 8B
- GLM-5.3 vs LFM2.5-2.6B
- gpt-oss-120b vs Granite 4.2 8B
- gpt-oss-120b vs LFM2.5-2.6B
- gpt-oss-20b vs Granite 4.2 8B
- gpt-oss-20b vs LFM2.5-2.6B
- Granite 4.2 30B vs Granite 4.2 8B
- Granite 4.2 30B vs LFM2.5-2.6B
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs LFM2.5-2.6B
- 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 LBS-27B
- 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 LFM2.5-2.6B
- Hy3 vs LFM2.5-2.6B
- Inkling-Small vs LFM2.5-2.6B
- Inkling vs LFM2.5-2.6B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM2.5-2.6B
- Kimi K3.1 Pro vs LFM2.5-2.6B
- Kimi K3 vs LFM2.5-2.6B
- Kolibri-1 vs LFM2.5-2.6B
- Kronos vs LFM2.5-2.6B
- Laguna M.1 vs LFM2.5-2.6B
- Laguna S 2.1 vs LFM2.5-2.6B
- Laguna XS 2.1 vs LFM2.5-2.6B
- LBS-27B vs LFM2.5-2.6B
- LFM2.5-2.6B vs LFM3-1.7B
- LFM2.5-2.6B vs LFM3-Audio-2B
- LFM2.5-2.6B vs LFM3-Omni-2B
- LFM2.5-2.6B vs LFM3-VL-2B
- LFM2.5-2.6B vs Ling-3.0-tiny
- LFM2.5-2.6B vs Ling-3.1-flash-1019
- LFM2.5-2.6B vs MiMo-V2.6 Distill Qwen 9B
- LFM2.5-2.6B vs MiniCPM-o 4.5
- LFM2.5-2.6B vs MiniCPM-V 4.7 1B
- LFM2.5-2.6B vs MiniCPM-V 4.7 35B-A3B
- LFM2.5-2.6B vs MiniCPM5-2B
- LFM2.5-2.6B vs MiniMax-M2.5
- LFM2.5-2.6B vs MiniMax-M2.7
- LFM2.5-2.6B vs MiniMax-M3.1-Flash
- LFM2.5-2.6B vs Mistral Large 4
- LFM2.5-2.6B vs Muse Glimmer 30B
- LFM2.5-2.6B vs Nanbeige4.3-33B
- LFM2.5-2.6B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- LFM2.5-2.6B vs Nemotron 3.5 Lightning 30B A3B
- LFM2.5-2.6B vs Nemotron 3 Nano 30B A3B
- LFM2.5-2.6B vs Nemotron 3 Nano 4B
- LFM2.5-2.6B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- LFM2.5-2.6B vs Nemotron 3 Super 120B A12B
- LFM2.5-2.6B vs Nemotron 3 Ultra 550B A55B
- LFM2.5-2.6B vs occamy-1.0
- LFM2.5-2.6B vs Olmo 3 7B Think
- LFM2.5-2.6B vs Ornith-1.5-122B
- LFM2.5-2.6B vs Ornith-1.5-35B-A3B
- LFM2.5-2.6B vs Ornith-1.5-397B
- LFM2.5-2.6B vs Ornith-1.5-9B
- LFM2.5-2.6B vs Qwen-AgentWorld-35B-A3B
- LFM2.5-2.6B vs Qwen3-30B-A3B-Instruct-2507
- LFM2.5-2.6B vs Qwen3-4B-Instruct-2507
- LFM2.5-2.6B vs Qwen3.5-0.8B
- LFM2.5-2.6B vs Qwen3.5-122B-A10B
- LFM2.5-2.6B vs Qwen3.5-2B
- LFM2.5-2.6B vs Qwen3.5-397B-A17B
- LFM2.5-2.6B vs Qwen3.5-4B
- LFM2.5-2.6B vs Qwen3.5-9B
- LFM2.5-2.6B vs Qwen3.6-27B
- LFM2.5-2.6B vs Qwen3.6-35B-A3B
- LFM2.5-2.6B vs Qwen3.8-27B
- LFM2.5-2.6B vs Qwen3.8-Flash-Next
- LFM2.5-2.6B vs Qwen3-Coder-30B-A3B-Instruct
- LFM2.5-2.6B vs Qwen3-Coder-Next
- LFM2.5-2.6B vs Qwen3-Omni-30B-A3B-Instruct
- LFM2.5-2.6B vs Qwen3-VL-2B-Instruct
- LFM2.5-2.6B vs Qwen3-VL-30B-A3B-Instruct
- LFM2.5-2.6B vs Qwen3-VL-32B-Instruct
- LFM2.5-2.6B vs Qwen3-VL-4B-Instruct
- LFM2.5-2.6B vs Qwen3-VL-8B-Instruct
- LFM2.5-2.6B vs Qwopus3.8-27B-Flash-V2
- LFM2.5-2.6B vs Recursive Flint
- LFM2.5-2.6B vs Ripple-65B Preview
- LFM2.5-2.6B vs SmolLM3-3B
- LFM2.5-2.6B vs Spark-X2.6-4B
- LFM2.5-2.6B vs Swift 1.5 Qwen3.8-27B
- LFM2.5-2.6B vs Swift 1.5 Qwen3.8-Flash-Next
- LFM2.5-2.6B vs ThinkingCap (Qwen3.8 27B)
- LFM2.5-2.6B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-8b-vs-lfm2-5-2-6b.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/lfm2-5-2-6b.json - From a terminal
anchor compare granite-4-2-8b lfm2-5-2-6b(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-8b", "b": "lfm2-5-2-6b"}at/mcp, no key