Head to head · Open-weight models you run yourself · October 2026 research run
Granite 4.2 3B vs LFM3-VL-2B
LFM3-VL-2B scores 61 (C) on agent readiness against Granite 4.2 3B's 59.8 (C), and leads in 1 of 4 scored categories. Granite 4.2 3B leads on reach, risk and documentation and upkeep. 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 on small hardware that want a permissive reasoning model for tool calls and coding, with thinking they can switch off
Ahead on
- Reach, 95 against 85
- Risk, 55 against 40
- Documentation and upkeep, 92 against 77
Watch for
No safety results published for 4.2, and only general safety cautions
Best for Agents on a laptop, phone or robot that need to read screens, documents, images and video from a model under 2 GB at 4 bits
Ahead on
- Agent interface, 90 against 85
Watch for
vLLM and SGLang support is unreleased, which the card says itself
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.
Risk Granite 4.2 3B +15
Granite 4.2 3B 55
File safety gets 15 of 25, safetensors only, less 10 because the card's vLLM command loads the repository's parser plugin. Provenance gets 15 for files in IBM's own organisation with hashes and a sigstore signature. Safety evaluation is 0, since 4.2 publishes no safety results. Agent guidance gets 5 for general cautions and the advice to add Granite Guardian. Apache 2.0 keeps licence risk at 15, and IBM's security.txt gives 5 of the security programme's 10.
LFM3-VL-2B 40
File safety 15, safetensors only, no .bin, .pt or .pth files (25). Provenance 15, files in the LiquidAI organisation, which Liquid's docs page for the model and its blog post link to (10). Safety evaluation 0, no safety results on the card or in Liquid's blog post for the LFM3 family, neither of which mentions safety testing. Agent guidance 0, Nothing on prompt injection, an instruction hierarchy, what refusals cover or safeguards to add. Licence risk 10, 15 less 5 for the $10M annual revenue threshold on commercial use. Security programme 0, no way to report a flaw found. 15 + 15 + 0 + 0 + 10 + 0 = 40.
Documentation and upkeep Granite 4.2 3B +15
Granite 4.2 3B 92
The card covers everything but a knowledge cut-off (17). IBM's disclosure lists the datasets with sources and sizes (20). The index file changed on 20 October 2026, 15 days before this check, and nothing in IBM's 4.2 repositories or the GitHub repository changed since (20). The two questions asked on IBM's 3B repositories have an IBM reply, and no new thread was opened after 21 October (20). Granite 4.1 3B stays in its own repository with no note (5), and the files agree with each other (10).
LFM3-VL-2B 77
Model card 17, Intended use (questions about video, documents, charts and app screens, finding objects, spatial reasoning), a limitation (not recommended for coding, multi-turn conversations or complex reasoning), architecture (language model, 14-layer vision encoder and projector), parameters (1.92B), context (128K) and 16 languages. Training data 5, A general description: the base's 22T tokens of pre-training with the kinds of data added since LFM2, then vision mid-training on image and video data, supervised fine-tuning, vision reinforcement learning and distillation. Last change 20, the last commit, on 9 November 2026, added the OpenVINO checkpoint to the card's inference table, a day before this check. Responsiveness 20, Of the 5 discussions that aren't pull requests (27 to 31 October 2026), 3 have a reply from a LiquidAI member, which is most. Version policy 5, LFM3 came out in new repositories and the LFM2.5 models stay in theirs. File health 10, Config, template and card agree on the lfm3_vl architecture, the 128,000-token context and the vision settings in processor_config.json. 17 + 5 + 20 + 20 + 5 + 10 = 77.
Reach Granite 4.2 3B +10
Granite 4.2 3B 95
Memory earns the full 30, since IBM's 4-bit MLX build is 2.07 GB and Ollama's Q4_K_M build 2.2 GB, about 2.5 to 2.6 GB with the fifth added. Five named runtimes run the granite architecture in released versions or their own libraries, so runtimes take the cap of 25, though LM Studio has no 4.2 entry. IBM's FP8, FP4, GGUF and MLX builds earn 15. Apache 2.0 with nothing added gives terms 15 and the ungated repositories download 10. Hosted too is 0, since only DeepInfra serves it and watsonx.ai stops at 4.1.
LFM3-VL-2B 85
Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB with its 0.20 GB projector file, and 1.30 GB × 1.2 = 1.6 GB, which fits 8 GB, well inside the 16 GB line. Runtimes 15, Released llama.cpp has the lfm3 architecture and the LFM3-VL projector (src/models/lfm3.cpp and tools/mtmd at b12242), Ollama's library has an lfm3-vl entry, and LM Studio's catalogue lists liquid/lfm3-vl-2b. Builds 15, Liquid's GGUF repository holds Q4_0, Q4_K_M, Q8_0, F16 and BF16 files, and Liquid publishes 4-bit and 8-bit MLX builds and an ONNX repository, all in the LiquidAI organisation. Terms 10, the LFM Open License v1.0, a custom licence that lets anyone use it commercially for free below a threshold of $10M annual revenue. Download 10, the Hub API reports gated false for the model and its GGUF, MLX and ONNX repositories on 10 November 2026, so the files download with no account and nothing to accept. Hosted 5, Liquid's own API lists lfm3-vl-2b among its models, so the publisher hosts it. 30 + 15 + 15 + 10 + 10 + 5 = 85.
Agent interface LFM3-VL-2B +5
Granite 4.2 3B 85
The template ships in the repository (20). The card shows how tools are declared and how calls come back, and names qwen3_coder for vLLM and SGLang (25). The template renders several calls in a turn (20). JSON output isn't documented for 4.2 (0). Thinking turns off or goes to low effort per request, with the reasoning returned apart in SGLang (10), and 131,072 tokens are native (10).
LFM3-VL-2B 90
Chat template 20, chat_template.jinja in the repository (12,129 characters), with roles, images and video, tools, deferred tools, tool results and the thinking switch. Tool-calling format 25, the card and Liquid's tool-use page document tools passed through tools= in apply_chat_template, calls returned as XML and results sent back as tool messages. Trained tool calling 20, the template loops over every entry in an assistant turn's tool_calls, so several calls fit in one turn, and the card says its fine-tuning mix included tool calling and agentic traces. Structured output 5, the card's vLLM and SGLang commands set a structured-output backend and its fine-tuning table has a JSON extraction notebook, but nothing says how to ask this model for JSON. Liquid's API guide documents response_format with lfm3-1.7b as its example. Reasoning control 10, Liquid's chat-template page documents enable_thinking=False in apply_chat_template for LFM3, with reasoning on by default inside think tags, and the card documents preserve_thinking and reports a no-thinking configuration in its benchmarks. Context 10, 128K tokens of input and output per the card, and max_position_embeddings 128000 for the language model in config.json. 20 + 25 + 20 + 5 + 10 + 10 = 90.
Score by category
| Category | Weight this run | Granite 4.2 3B | LFM3-VL-2B | Edge |
|---|---|---|---|---|
| Capability | 35%pending | pending | pending | not scored in this run |
| Reach | 25%25 | 95 | 85 | Granite 4.2 3B +10 |
| Risk | 20%20 | 55 | 40 | Granite 4.2 3B +15 |
| Agent interface | 10%10 | 85 | 90 | LFM3-VL-2B +5 |
| Documentation and upkeep | 10%10 | 92 | 77 | Granite 4.2 3B +15 |
| Negative events | ≤15 | 0 | 0 | |
| Total | C 59.8/100 | C 61/100 |
Facts side by side
| Fact | Granite 4.2 3B | LFM3-VL-2B |
|---|---|---|
| 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 | 2026-11-09 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Agent reviews | 3.8/5 (4) | none |
Verdicts
Granite 4.2 3B
A small reasoning model for tool calls, coding and multilingual chat, published by IBM under plain Apache 2.0 with signed files and a dataset disclosure, and run by llama.cpp, Ollama, vLLM, SGLang and Transformers from a 2.2 GB Ollama build. Thinking turns off or shortens per request. It has no published safety results and no documented JSON mode.
LFM3-VL-2B
A 1.92B vision model that reads images and video on an 8 GB machine, with a documented tool-call format and thinking. It runs today in llama.cpp, Ollama and LM Studio, while vLLM and SGLang support is still unreleased. Transformers needs repository code, and there are no safety results, security contact or data sources.
Before you call either
Granite 4.2 3B
- Start it with
ollama run granite4.2:3b; set options.num_ctx in the request, since Ollama's default context is short and the model takes up to 131,072 - With vLLM 0.32.0 or later, serve
ibm-granite/granite-4.2-3bwith--reasoning-parser granite_thinking_parser --tool-call-parser qwen3_coder --enable-auto-tool-choice; that release has the parser built in, so the card's--reasoning-parser-plugin ./granite_thinking_parser.pyisn't needed - With SGLang 0.5.18 or later,
--reasoning-parser auto --tool-call-parser autoresolve to IBM's recommended parsers, and the reasoning comes back in reasoning_content - Use temperature 1.0 and top_p 0.95 for every mode, as IBM requires
- Pass
enable_thinkingfalse for direct answers orlow_efforttrue for short reasoning, through chat_template_kwargs on an OpenAI-compatible server - Earlier turns' thinking is stripped by default (
truncate_history_thinking), so pass it false to keep reasoning in multi-turn history - For JSON, use the runtime's guided decoding, since IBM documents no JSON mode for 4.2
- Verify the files with
python -m model_signing verify sigstoreand IBM's identity, per IBM's signature guide
LFM3-VL-2B
- Start it with
llama-server -hf LiquidAI/LFM3-VL-2B-GGUF:Q4_K_M --jinjaorollama run lfm3-vl, with llama.cpp b11960 or later - Use temperature 0.1, top_k 50 and repetition penalty 1.1, per the card
- Video is sampled at 2 frames a second up to 768 frames, and each frame costs context. Video input in llama.cpp needs ffmpeg
- Don't plan on vLLM or SGLang until a release carries LFM3-VL
- Validate JSON output yourself
- Liquid doesn't recommend it for coding, multi-turn conversations or complex reasoning
Questions
Which is better for AI agents, Granite 4.2 3B or LFM3-VL-2B?
LFM3-VL-2B scores 61 (C) on agent readiness against Granite 4.2 3B's 59.8 (C), and leads in 1 of 4 scored categories. Granite 4.2 3B leads on reach, risk and documentation and upkeep.
Other comparisons with Granite 4.2 3B or LFM3-VL-2B
- Agents-A1-4B vs Granite 4.2 3B
- Agents-A1-4B vs LFM3-VL-2B
- Apertus v1.5 8B vs Granite 4.2 3B
- Apertus v1.5 8B vs LFM3-VL-2B
- Apodex-1.1-mini vs Granite 4.2 3B
- Apodex-1.1-mini vs LFM3-VL-2B
- Arete-27B vs Granite 4.2 3B
- Arete-27B vs LFM3-VL-2B
- BigBang-v1 vs Granite 4.2 3B
- BigBang-v1 vs LFM3-VL-2B
- Carbon-X vs Granite 4.2 3B
- Carbon-X vs LFM3-VL-2B
- Cosmos-Reason2-2B vs Granite 4.2 3B
- Cosmos-Reason2-2B vs LFM3-VL-2B
- Darwin-36B-Opus vs Granite 4.2 3B
- Darwin-36B-Opus vs LFM3-VL-2B
- DeepSeek-V3.2 vs Granite 4.2 3B
- DeepSeek-V3.2 vs LFM3-VL-2B
- DeepSeek V4.1 Flash vs Granite 4.2 3B
- DeepSeek V4.1 Flash vs LFM3-VL-2B
- DeepSeek-V4-Flash-0731 vs Granite 4.2 3B
- DeepSeek-V4-Flash-0731 vs LFM3-VL-2B
- DiffusionGemma 26B A4B IT vs Granite 4.2 3B
- DiffusionGemma 26B A4B IT vs LFM3-VL-2B
- Gemma 4 12B IT vs Granite 4.2 3B
- Gemma 4 12B IT vs LFM3-VL-2B
- Gemma 4 26B A4B IT vs Granite 4.2 3B
- Gemma 4 26B A4B IT vs LFM3-VL-2B
- Gemma 4 31B IT vs Granite 4.2 3B
- Gemma 4 31B IT vs LFM3-VL-2B
- Gemma 4 E2B IT vs Granite 4.2 3B
- Gemma 4 E2B IT vs LFM3-VL-2B
- Gemma 4 E4B IT vs Granite 4.2 3B
- Gemma 4 E4B IT vs LFM3-VL-2B
- GLM-4.5-Air vs Granite 4.2 3B
- GLM-4.5-Air vs LFM3-VL-2B
- GLM-4.7-Flash vs Granite 4.2 3B
- GLM-4.7-Flash vs LFM3-VL-2B
- GLM-5.3-Flash vs Granite 4.2 3B
- GLM-5.3-Flash vs LFM3-VL-2B
- GLM-5.3 vs Granite 4.2 3B
- GLM-5.3 vs LFM3-VL-2B
- gpt-oss-120b vs Granite 4.2 3B
- gpt-oss-120b vs LFM3-VL-2B
- gpt-oss-20b vs Granite 4.2 3B
- gpt-oss-20b vs LFM3-VL-2B
- Granite 4.2 30B vs Granite 4.2 3B
- Granite 4.2 30B vs LFM3-VL-2B
- Granite 4.2 3B vs Granite 4.2 8B
- Granite 4.2 3B vs Hy-Memory-30B-A3B
- Granite 4.2 3B vs Hy3
- Granite 4.2 3B vs Inkling
- Granite 4.2 3B vs Inkling-Small
- Granite 4.2 3B vs InternVL3.5-GPT-OSS-20B-A4B-Preview
- Granite 4.2 3B vs Kimi K3
- Granite 4.2 3B vs Kimi K3.1 Pro
- Granite 4.2 3B vs Kolibri-1
- Granite 4.2 3B vs Kronos
- Granite 4.2 3B vs Laguna M.1
- Granite 4.2 3B vs Laguna S 2.1
- Granite 4.2 3B vs Laguna XS 2.1
- Granite 4.2 3B vs LBS-27B
- Granite 4.2 3B vs LFM2.5-2.6B
- Granite 4.2 3B vs LFM3-1.7B
- Granite 4.2 3B vs LFM3-Audio-2B
- Granite 4.2 3B vs LFM3-Omni-2B
- Granite 4.2 3B vs Ling-3.0-tiny
- Granite 4.2 3B vs Ling-3.1-flash-1019
- Granite 4.2 3B vs MiMo-V2.6 Distill Qwen 9B
- Granite 4.2 3B vs MiniCPM-o 4.5
- Granite 4.2 3B vs MiniCPM-V 4.7 1B
- Granite 4.2 3B vs MiniCPM-V 4.7 35B-A3B
- Granite 4.2 3B vs MiniCPM5-2B
- Granite 4.2 3B vs MiniMax-M2.5
- Granite 4.2 3B vs MiniMax-M2.7
- Granite 4.2 3B vs MiniMax-M3.1-Flash
- Granite 4.2 3B vs Mistral Large 4
- Granite 4.2 3B vs Muse Glimmer 30B
- Granite 4.2 3B vs Nanbeige4.3-33B
- Granite 4.2 3B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- Granite 4.2 3B vs Nemotron 3.5 Lightning 30B A3B
- Granite 4.2 3B vs Nemotron 3 Nano 30B A3B
- Granite 4.2 3B vs Nemotron 3 Nano 4B
- Granite 4.2 3B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- Granite 4.2 3B vs Nemotron 3 Super 120B A12B
- Granite 4.2 3B vs Nemotron 3 Ultra 550B A55B
- Granite 4.2 3B vs occamy-1.0
- Granite 4.2 3B vs Olmo 3 7B Think
- Granite 4.2 3B vs Ornith-1.5-122B
- Granite 4.2 3B vs Ornith-1.5-35B-A3B
- Granite 4.2 3B vs Ornith-1.5-397B
- Granite 4.2 3B vs Ornith-1.5-9B
- Granite 4.2 3B vs Qwen-AgentWorld-35B-A3B
- Granite 4.2 3B vs Qwen3-30B-A3B-Instruct-2507
- Granite 4.2 3B vs Qwen3-4B-Instruct-2507
- Granite 4.2 3B vs Qwen3.5-0.8B
- Granite 4.2 3B vs Qwen3.5-122B-A10B
- Granite 4.2 3B vs Qwen3.5-2B
- Granite 4.2 3B vs Qwen3.5-397B-A17B
- Granite 4.2 3B vs Qwen3.5-4B
- Granite 4.2 3B vs Qwen3.5-9B
- Granite 4.2 3B vs Qwen3.6-27B
- Granite 4.2 3B vs Qwen3.6-35B-A3B
- Granite 4.2 3B vs Qwen3.8-27B
- Granite 4.2 3B vs Qwen3.8-Flash-Next
- Granite 4.2 3B vs Qwen3-Coder-30B-A3B-Instruct
- Granite 4.2 3B vs Qwen3-Coder-Next
- Granite 4.2 3B vs Qwen3-Omni-30B-A3B-Instruct
- Granite 4.2 3B vs Qwen3-VL-2B-Instruct
- Granite 4.2 3B vs Qwen3-VL-30B-A3B-Instruct
- Granite 4.2 3B vs Qwen3-VL-32B-Instruct
- Granite 4.2 3B vs Qwen3-VL-4B-Instruct
- Granite 4.2 3B vs Qwen3-VL-8B-Instruct
- Granite 4.2 3B vs Qwopus3.8-27B-Flash-V2
- Granite 4.2 3B vs Recursive Flint
- Granite 4.2 3B vs Ripple-65B Preview
- Granite 4.2 3B vs SmolLM3-3B
- Granite 4.2 3B vs Spark-X2.6-4B
- Granite 4.2 3B vs Swift 1.5 Qwen3.8-27B
- Granite 4.2 3B vs Swift 1.5 Qwen3.8-Flash-Next
- Granite 4.2 3B vs ThinkingCap (Qwen3.8 27B)
- Granite 4.2 3B vs Baidu Unlimited-OCR-2
- Granite 4.2 8B vs LFM3-VL-2B
- Hy-Memory-30B-A3B vs LFM3-VL-2B
- Hy3 vs LFM3-VL-2B
- Inkling-Small vs LFM3-VL-2B
- Inkling vs LFM3-VL-2B
- InternVL3.5-GPT-OSS-20B-A4B-Preview vs LFM3-VL-2B
- Kimi K3.1 Pro vs LFM3-VL-2B
- Kimi K3 vs LFM3-VL-2B
- Kolibri-1 vs LFM3-VL-2B
- Kronos vs LFM3-VL-2B
- Laguna M.1 vs LFM3-VL-2B
- Laguna S 2.1 vs LFM3-VL-2B
- Laguna XS 2.1 vs LFM3-VL-2B
- LBS-27B vs LFM3-VL-2B
- LFM2.5-2.6B vs LFM3-VL-2B
- LFM3-1.7B vs LFM3-VL-2B
- LFM3-Audio-2B vs LFM3-VL-2B
- LFM3-Omni-2B vs LFM3-VL-2B
- LFM3-VL-2B vs Ling-3.0-tiny
- LFM3-VL-2B vs Ling-3.1-flash-1019
- LFM3-VL-2B vs MiMo-V2.6 Distill Qwen 9B
- LFM3-VL-2B vs MiniCPM-o 4.5
- LFM3-VL-2B vs MiniCPM-V 4.7 1B
- LFM3-VL-2B vs MiniCPM-V 4.7 35B-A3B
- LFM3-VL-2B vs MiniCPM5-2B
- LFM3-VL-2B vs MiniMax-M2.5
- LFM3-VL-2B vs MiniMax-M2.7
- LFM3-VL-2B vs MiniMax-M3.1-Flash
- LFM3-VL-2B vs Mistral Large 4
- LFM3-VL-2B vs Muse Glimmer 30B
- LFM3-VL-2B vs Nanbeige4.3-33B
- LFM3-VL-2B vs NVIDIA Nemotron 3.5 Bolt E4B 4GB
- LFM3-VL-2B vs Nemotron 3.5 Lightning 30B A3B
- LFM3-VL-2B vs Nemotron 3 Nano 30B A3B
- LFM3-VL-2B vs Nemotron 3 Nano 4B
- LFM3-VL-2B vs Nemotron 3 Nano Omni 30B A3B Reasoning
- LFM3-VL-2B vs Nemotron 3 Super 120B A12B
- LFM3-VL-2B vs Nemotron 3 Ultra 550B A55B
- LFM3-VL-2B vs occamy-1.0
- LFM3-VL-2B vs Olmo 3 7B Think
- LFM3-VL-2B vs Ornith-1.5-122B
- LFM3-VL-2B vs Ornith-1.5-35B-A3B
- LFM3-VL-2B vs Ornith-1.5-397B
- LFM3-VL-2B vs Ornith-1.5-9B
- LFM3-VL-2B vs Qwen-AgentWorld-35B-A3B
- LFM3-VL-2B vs Qwen3-30B-A3B-Instruct-2507
- LFM3-VL-2B vs Qwen3-4B-Instruct-2507
- LFM3-VL-2B vs Qwen3.5-0.8B
- LFM3-VL-2B vs Qwen3.5-122B-A10B
- LFM3-VL-2B vs Qwen3.5-2B
- LFM3-VL-2B vs Qwen3.5-397B-A17B
- LFM3-VL-2B vs Qwen3.5-4B
- LFM3-VL-2B vs Qwen3.5-9B
- LFM3-VL-2B vs Qwen3.6-27B
- LFM3-VL-2B vs Qwen3.6-35B-A3B
- LFM3-VL-2B vs Qwen3.8-27B
- LFM3-VL-2B vs Qwen3.8-Flash-Next
- LFM3-VL-2B vs Qwen3-Coder-30B-A3B-Instruct
- LFM3-VL-2B vs Qwen3-Coder-Next
- LFM3-VL-2B vs Qwen3-Omni-30B-A3B-Instruct
- LFM3-VL-2B vs Qwen3-VL-2B-Instruct
- LFM3-VL-2B vs Qwen3-VL-30B-A3B-Instruct
- LFM3-VL-2B vs Qwen3-VL-32B-Instruct
- LFM3-VL-2B vs Qwen3-VL-4B-Instruct
- LFM3-VL-2B vs Qwen3-VL-8B-Instruct
- LFM3-VL-2B vs Qwopus3.8-27B-Flash-V2
- LFM3-VL-2B vs Recursive Flint
- LFM3-VL-2B vs Ripple-65B Preview
- LFM3-VL-2B vs SmolLM3-3B
- LFM3-VL-2B vs Spark-X2.6-4B
- LFM3-VL-2B vs Swift 1.5 Qwen3.8-27B
- LFM3-VL-2B vs Swift 1.5 Qwen3.8-Flash-Next
- LFM3-VL-2B vs ThinkingCap (Qwen3.8 27B)
- LFM3-VL-2B vs Baidu Unlimited-OCR-2
Machine-readable
- This page as Markdown
/compare/granite-4-2-3b-vs-lfm3-vl-2b.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/granite-4-2-3b.json·/api/v1/tools/lfm3-vl-2b.json - From a terminal
anchor compare granite-4-2-3b lfm3-vl-2b(the CLI) - Over MCP
compare_tools {"a": "granite-4-2-3b", "b": "lfm3-vl-2b"}at/mcp, no key