# LFM3-Omni-2B (slim)

> LFM3-Omni-2B is Liquid AI's open-weight 2.17B omni model for on-device use, taking text, images, video and audio and answering in text or speech, with tool calling and a 32K-token context, released on 27 October 2026 with GGUF and MLX builds.

- Full: https://www.anchorterminal.com/tools/lfm3-omni-2b.md (~9,850 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/tools/lfm3-omni-2b.json · canonical https://www.anchorterminal.com/tools/lfm3-omni-2b
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-10 · pricing https://www.anchorterminal.com/tools/lfm3-omni-2b#pricing · reviews https://www.anchorterminal.com/tools/lfm3-omni-2b#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**C · 61/100 · rank #65 of 135 open-weight models · #55 in Open-weight models · not agent-ready · confidence low**


Assessment: One 2.17B model that sees, listens and talks on an 8 GB machine and turns spoken requests into tool calls. Only llama.cpp and Ollama run it in a release. The context is 32K, it doesn't reason, Liquid hasn't answered a question on the repository, and there are no safety results or data sources.

## Facts

- Kind: Open-weight model · vendor: Liquid AI · category: Open-weight models · legal entity: Liquid AI, Inc. (the licensor named in the LFM Open License) · provenance 73/100
- Packages: huggingface `LiquidAI/LFM3-Omni-2B`, huggingface `LiquidAI/LFM3-Omni-2B-GGUF`, huggingface `LiquidAI/LFM3-Omni-2B-MLX-4bit`, ollama `lfm3-omni`
- Auth: None · pricing: Free · x402: no · licence: LFM Open License v1.0 (free commercial use below $10M annual revenue)
- Benchmark probes: not run yet, so Performance is pending
- Surface graded: The open weights at huggingface.co/LiquidAI/LFM3-Omni-2B and Liquid's GGUF, MLX and ONNX repositories, read from the model card, the files and their metadata, the chat template, the head of the licence, Liquid's docs and blog post, Ollama's library, LM Studio's catalogue and the runtimes' own code at their latest releases on 10 November 2026. Liquid's licence terms, company pages and security.txt were read for the LFM2.5-2.6B listing on 21 October and 4 November, and security.txt again today. Nothing was downloaded or run
- Model: 2,166,928,384 parameters in the files (2.17B on the card): the LFM3 backbone, Liquid's vision encoder, a causal audio encoder and the LiquidCodec audio tokenizer. Text, images, video with or without its soundtrack and 16 kHz audio in; text, 24 kHz speech or the two interleaved out. Video is sampled at 2 frames a second, 4 to 384 frames. It doesn't reason
- Built on: The LFM3 backbone, per the card. The repository's metadata names no base model, and the licence is the same LFM Open License v1.0
- Files: Safetensors in BF16 (4.50 GB for the repository) with chat_template.jinja, config, tokenizer, a LICENSE file and 14 Python files that Transformers loads as the model's code. No pickle files. Hugging Face lists a SHA-256 for each of the 5 large files
- Licence: LFM Open License v1.0, Apache-like terms (copyright and patent grants, redistribution with notices) with a commercial-use limit. Commercial use is licensed only for legal entities under $10M in annual revenue, as read in full for the LFM2.5-2.6B listing. The LICENSE file is in the repository
- Runtimes: Released llama.cpp has the lfm3 architecture with the LFM3 vision and audio projectors and speech output (src/models/lfm3.cpp and tools/mtmd at b12242, with a realtime client example), and Ollama's library has an lfm3-omni entry. The card names SGLang for text output, and SGLang 0.5.23 has no lfm3 code. vLLM 0.33.0 has none, Transformers 5.22.2 loads it only through the repository's own Python, and LM Studio's catalogue has no entry for it. The card asks for transformers 5.20.2 or later with trust_remote_code
- Context: 32K tokens of input and output per the card. config.json gives the language model 128,000 positions and Liquid's API lists the hosted model at 128,000, but the card's figure is the one counted
- Tools and reasoning: Tools go in through `tools=` in apply_chat_template and calls come back as XML, a superset of the qwen3_coder format, which Liquid's docs name as the parser for vLLM. Tools marked `defer_loading` stay out of the prompt until a search tool returns them. The card says this is a non-reasoning model and that `enable_thinking=True` is not supported, so there is no thinking to turn off or budget
- Hardware: No memory figure on the card. Liquid's Q4_K_M GGUF is 1.10 GB with its 0.29 GB projector file, its Q8_0 1.85 GB, its 4-bit MLX build 2.11 GB and the BF16 files 4.49 GB. Liquid also publishes an ONNX repository. It has no FP8 or NVFP4 build of this model
- Training data: The card has no training section. Liquid's blog post describes the shared LFM3 backbone's 22T tokens of pre-training in general terms and says nothing about the audio, vision or speech data this model was trained on. No sources or cut-off
- Languages: 16 text languages and 19 speech languages and locales, listed on the card

- Scores: Capability pending, Reach 80, Risk 40, Agent interface 70, Documentation and upkeep 49 · total over the 7 assessed categories
- Why:  · Reach, Memory 30, Liquid's Q4_K_M GGUF is 1.10 GB with its 0.29 GB projector file, and 1.39 GB × 1.2 = 1.7 GB, which fits 8 GB, well inside the 16… · Risk, File safety 15, safetensors only, no .bin, .pt or .pth files (25). · Agent interface, Chat template 20, chat_template.jinja in the repository (13,513 characters), with roles, images, video and audio, tools, deferred tools and… · Documentation and upkeep, Model card 14, Intended use (one on-device model in place of separate speech recognition, vision, language and speech models), architecture…
- Sources: 26, open questions: 6, both in the full twin
- Capabilities: model.open-weights
- JSON: https://www.anchorterminal.com/api/v1/tools/lfm3-omni-2b.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.
- Support: Discord https://discord.gg/DFU3WQeaYD; https://docs.liquid.ai/lfm/models/lfm3-omni-2b; more in the full twin

## Before you call it

1. Start it with `llama-server -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M --jinja` or `ollama run lfm3-omni`
2. Greedy decoding for text. For speech use audio_temperature 0.4 and audio_repetition_penalty 1.2, per the card
3. The context is 32K, and llama.cpp samples video at 2 frames a second up to 384 frames
4. Parse tool calls yourself from the XML it returns
5. It doesn't reason, so don't pass enable_thinking
6. Validate JSON output yourself

## Connect

```bash
llama-server -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M --jinja
# or
ollama run lfm3-omni
```

```bash
curl http://localhost:8080/v1/chat/completions \
  -H 'Content-Type: application/json' \
  -d '{"messages": [{"role": "user", "content": "Hello!"}]}'
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Qwen3-Embedding-8B | BB | 75.4 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-8b.min.md |
| Gemma 4 31B IT | BB | 74.1 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-31b-it.min.md |
| Qwen3-Embedding-4B | BB | 73.6 | model.open-weights | https://www.anchorterminal.com/tools/qwen3-embedding-4b.min.md |
| Gemma 4 12B IT | BB | 72.3 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-12b-it.min.md |
| Gemma 4 26B A4B IT | BB | 72.2 | model.open-weights | https://www.anchorterminal.com/tools/gemma-4-26b-a4b-it.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)