# LFM3-Omni-2B

> LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model.

- **Organisation:** LiquidAI
- **Category:** Omni / Any-to-Any
- **Parameters:** 2.2B
- **Context length:** 128,000 tokens
- **Licence:** lfm1.0 (Commercial use with conditions)
- **Released:** 2026-10-21
- **Hugging Face:** 28.3K downloads (30 days), 635 likes
- **Ollama:** `ollama run lfm3-omni:2b`

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 1.57 |
| Q3_K_M | 1.91 |
| Q4_K_M | 2.16 |
| Q5_K_M | 2.38 |
| Q6_K | 2.62 |
| Q8_0 | 3.13 |
| F16 | 5.11 |

## Runs with

- [llama.cpp](https://selfhost.directory/project/llamacpp)
- [LM Studio](https://lmstudio.ai)
- [MLX](https://github.com/ml-explore/mlx-lm)
- [Ollama](https://selfhost.directory/project/ollama)
- [Transformers](https://github.com/huggingface/transformers)
- [Jan](https://jan.ai) (community)
- [KoboldCpp](https://selfhost.directory/project/koboldcpp) (community)
- [LocalAI](https://selfhost.directory/project/localai) (community)
- [ONNX Runtime](https://onnxruntime.ai) (community)

## About

LFM3-Omni-2B is Liquid AI's first omni-modal model in the LFM3 family: a single end-to-end model that understands text, images, video and audio, and answers in text and speech. It is built for on-device use: one model replaces a separate ASR model, vision-language model, LLM and TTS model.

• Any input, text or speech output: ask about a photo by voice, transcribe or translate speech, chat out loud, or ask questions about a video and its soundtrack together.
• Watches and listens together: for videos with sound, the model sees and hears them at the same time, so it can answer questions that need both.
• Small enough for devices: at 2.2B parameters, it is designed to run efficiently on phones, laptops and other edge hardware.

Find more information about the LFM3 family in our release blog post.

The LFM3 family includes base, text, vision, audio, omni, and decision models.

## Alternatives

- [LiquidAI/d1-Omni-2B](https://selfhost.directory/models/liquidai/d1-omni-2b) (2.2B, lfm1.0, ≈2.16 GB at Q4): d1-Omni-2B is a decision model for text, pictures, and audio, built on LFM3-Omni-2B. It returns calibrated answers in one forward pass, without generating tokens.
- [LiquidAI/LFM3-Audio-2B](https://selfhost.directory/models/liquidai/lfm3-audio-2b) (2B, lfm1.0, ≈2.2 GB at Q4): LFM3-Audio-2B is a compact, fully featured audio model that runs locally on laptops and edge devices. It takes text or audio as input and responds with text, speech, or both.
- [google/gemma-4-E2B-it](https://selfhost.directory/models/google/gemma-4-e2b-it) (5.1B, Apache 2.0, ≈3.81 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [google/gemma-4-E4B-it](https://selfhost.directory/models/google/gemma-4-e4b-it) (8B, Apache 2.0, ≈5.9 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [google/gemma-4-E2B](https://selfhost.directory/models/google/gemma-4-e2b) (5.1B, Apache 2.0, ≈3.81 GB at Q4): Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input (with audio supported on E2B, E4B, and 12B) and generating text output. This release includes open-weights models in both pre-trained and instruction-tuned variants.
- [deepseek-ai/Janus-1.3B](https://selfhost.directory/models/deepseek-ai/janus-1.3b) (2.1B, MIT, ≈3.24 GB at Q4): Janus is a novel autoregressive framework that unifies multimodal understanding and generation. It addresses the limitations of previous approaches by decoupling visual encoding into separate pathways, while still utilizing a single, unified transformer architecture for processing.

More: https://selfhost.directory/models/liquidai/lfm3-omni-2b/alternatives

## Runs well on

- [GeForce RTX 4060](https://selfhost.directory/models/liquidai/lfm3-omni-2b/on/rtx-4060): F16, est. 35 tok/s
- [Apple M4 (16 GB)](https://selfhost.directory/models/liquidai/lfm3-omni-2b/on/apple-m4-16gb): F16, est. 15 tok/s
- [Radeon RX 6700 XT](https://selfhost.directory/models/liquidai/lfm3-omni-2b/on/rx-6700-xt): F16, est. 49 tok/s
- [GeForce RTX 3060 12GB](https://selfhost.directory/models/liquidai/lfm3-omni-2b/on/rtx-3060): F16, est. 46 tok/s
- [Arc B580](https://selfhost.directory/models/liquidai/lfm3-omni-2b/on/arc-b580): F16, est. 58 tok/s
- [Tesla T4](https://selfhost.directory/models/liquidai/lfm3-omni-2b/on/tesla-t4): F16, est. 41 tok/s

## Similar size

- [LiquidAI/LFM3-Audio-2B](https://selfhost.directory/models/liquidai/lfm3-audio-2b) (2B)
- [LiquidAI/d1-Omni-2B](https://selfhost.directory/models/liquidai/d1-omni-2b) (2.2B)
- [deepseek-ai/Janus-1.3B](https://selfhost.directory/models/deepseek-ai/janus-1.3b) (2.1B)
- [deepseek-ai/JanusFlow-1.3B](https://selfhost.directory/models/deepseek-ai/janusflow-1.3b) (2B)
- [lmms-lab/Aero-1-Audio](https://selfhost.directory/models/lmms-lab/aero-1-audio) (2.4B)

## FAQ

**How much VRAM does LFM3-Omni-2B need?**
About 2.2 GB at Q4_K_M with an 8K context. Q8_0 needs about 3.1 GB and full precision about 5.1 GB. Longer contexts need more memory for the KV cache.

**Can LFM3-Omni-2B run on the RTX 4060?**
Yes. It fits at FP16 / BF16 (about 4.3 GB), at an estimated 35 tokens/s. It fits comfortably on the Apple M4 (16 GB), Radeon RX 6700 XT, RTX 3060 12GB.

**Can I use LFM3-Omni-2B commercially?**
Yes, with conditions. It is released under lfm1.0. Custom licence: read the model card before using it commercially.

**What is the context length of LFM3-Omni-2B?**
128,000 tokens (125K). The full window needs far more memory than an 8K context.

**How do I run LFM3-Omni-2B with Ollama or llama.cpp?**
With Ollama: ollama run lfm3-omni:2b. With llama.cpp: llama-server -hf LiquidAI/LFM3-Omni-2B-GGUF:Q4_K_M, which starts an OpenAI-compatible server.

## Links

- huggingface: https://huggingface.co/LiquidAI/LFM3-Omni-2B
- homepage: https://www.liquid.ai/
- ollama: https://ollama.com/library/lfm3-omni

---
Source: https://selfhost.directory/models/liquidai/lfm3-omni-2b