---
title: LFM3-Omni-2B-MLX-bf16
canonical_url: "https://www.modelscope.cn/models/LiquidAI/LFM3-Omni-2B-MLX-bf16"
md_url: "https://www.modelscope.cn/models/LiquidAI/LFM3-Omni-2B-MLX-bf16.md"
repository: LiquidAI/LFM3-Omni-2B-MLX-bf16
last_updated: 2026-10-28
license: other
pipeline_tag: any-to-any
tasks:
  - any-to-any
model_type:
  - lfm3_omni
architectures:
  - Lfm3OmniForConditionalGeneration
base_model:
  - LiquidAI/LFM3-Omni-2B
base_model_relation: quantized
parameters: 2.2B
tensor_type:
  - BF16
library_name:
  - mlx
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
  - ar
  - zh
  - fr
  - de
  - it
  - ja
  - ko
  - pt
  - es
  - vi
  - th
  - id
  - hi
  - ru
  - pl
  - da
  - el
  - fi
  - he
  - nl
  - sv
  - tr
downloads: 8
stars: 0
tags:
  - liquid
  - lfm3
  - lfm3-omni
  - omni
  - audio
  - vision
  - speech-to-speech
  - mlx
---

# LFM3-Omni-2B-MLX-bf16

> LFM3-Omni-2B-MLX-bf16 - LiquidAI 在 ModelScope 开源的模型。LFM3-Omni-2B-MLX-bf16

LiquidAI/LFM3-Omni-2B-MLX-bf16 是 ModelScope 魔搭社区上的 2.2B 参数any-to-any模型，采用 other 许可，基于 LiquidAI/LFM3-Omni-2B 构建。

- **Repository**: LiquidAI/LFM3-Omni-2B-MLX-bf16
- **License**: other
- **Tasks**: any-to-any
- **Parameters**: 2.2B
- **Base model**: LiquidAI/LFM3-Omni-2B
- **Tags**: liquid, lfm3, lfm3-omni, omni, audio, vision, speech-to-speech, mlx
- **Downloads**: 8
- **Stars**: 0
- **Last updated**: 2026-10-28

Source: https://www.modelscope.cn/models/LiquidAI/LFM3-Omni-2B-MLX-bf16

---

<div align="center">
  <img
    src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/liquid-ai-banner.webp"
    alt="Liquid AI"
    style="width: 100%; max-width: 100%; height: auto; display: block; margin: 0;"
  />
  <div align="center" style="display: flex; justify-content: center; align-items: center; gap: 1.25em; margin: 8px 0 1.7rem; padding: 0; line-height: 1.3;">
    <a href="https://console.liquid.ai/dashboard" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/api.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>API</strong></a>
    <a href="https://playground.liquid.ai/" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/try.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>Try</strong></a>
    <a href="https://docs.liquid.ai/lfm/getting-started/welcome" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/docs.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>Docs</strong></a>
    <a href="https://www.liquid.ai/blog/lfm3" style="display: inline-flex; align-items: center; gap: 6px;"><img src="https://huggingface.co/LiquidAI/LFM3-1.7B/resolve/main/assets/icons/blog.svg" width="16" height="16" alt="" aria-hidden="true" style="display: block; flex: 0 0 16px; width: 16px; height: 16px; margin: 0;" /><strong>Blog</strong></a>
  </div>
</div>

# LFM3-Omni-2B-MLX-bf16

BF16 MLX version of [LFM3-Omni-2B](https://huggingface.co/LiquidAI/LFM3-Omni-2B) for Apple Silicon. The weights take 4.33 GB, plus 0.15 GB for the audio codec in `audio_tokenizer/`.

Weights are stored in BF16, as in the original checkpoint.

Find architecture and usage details in the [original model card](https://huggingface.co/LiquidAI/LFM3-Omni-2B).

## Use with MLX-VLM
<hr style="margin: -0.7em 0 1.2em 0; border: 0; border-top: 1px solid rgba(127, 127, 127, 0.3);" />

Support for LFM3-Omni in [MLX-VLM](https://github.com/Blaizzy/mlx-vlm) is in progress. We will update this card when an MLX-VLM release supports it.

```bash
# Speech recognition
python -m mlx_vlm.generate --model LiquidAI/LFM3-Omni-2B-MLX-bf16 --temperature 0 \
  --system "Perform ASR in English." --prompt "" --audio speech.wav

# Text to speech (24 kHz WAV)
python -m mlx_vlm.generate --model LiquidAI/LFM3-Omni-2B-MLX-bf16 \
  --system "Perform TTS in American English using a female voice." \
  --prompt "The quick brown fox jumps over the lazy dog." \
  --output-modality audio --output tts.wav

# Image question
python -m mlx_vlm.generate --model LiquidAI/LFM3-Omni-2B-MLX-bf16 --temperature 0 \
  --system "Answer questions about the provided image. Base every answer only on what can be seen. Respond with text." \
  --image image.png --prompt "What does the sign say?"
```

Text answers use greedy decoding (`--temperature 0`). Speech output samples with `audio_temperature=0.4` and `audio_repetition_penalty=1.2` by default. The original model card lists the voices, languages and other system prompts. More options in the [MLX guide](https://docs.liquid.ai/deployment/on-device/mlx).