Automatic Speech Recognition
MLX
Safetensors
Chinese
English
qwen2
apple-silicon
speech-recognition
mimo
4-bit precision
Instructions to use mlx-community/MiMo-V2.5-ASR-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use mlx-community/MiMo-V2.5-ASR-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir MiMo-V2.5-ASR-MLX-4bit mlx-community/MiMo-V2.5-ASR-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
metadata
license: apache-2.0
library_name: mlx
pipeline_tag: automatic-speech-recognition
base_model:
- XiaomiMiMo/MiMo-V2.5-ASR
tags:
- mlx
- apple-silicon
- automatic-speech-recognition
- speech-recognition
- mimo
language:
- zh
- en
Part of the MiMo V2.5 ASR MLX collection.
MiMo-V2.5-ASR-MLX-4bit (MLX)
Apple MLX weights for XiaomiMiMo/MiMo-V2.5-ASR, converted for local ASR on Apple Silicon.
TL;DR
| Variant | 4-bit |
| Best for | smallest checkpoint |
| Official code | XiaomiMiMo/MiMo-V2.5-ASR |
| MLX helper | ailuntx/MiMo-V2.5-ASR-MLX |
| MLX runtime dependency | ailuntx/mlx-audio |
| Audio tokenizer | mlx-community/MiMo-Audio-Tokenizer |
| Hardware | Apple Silicon recommended; HF Spaces CPU fallback is only a load smoke test |
Quick Start
git clone https://github.com/ailuntx/MiMo-V2.5-ASR-MLX.git
cd MiMo-V2.5-ASR-MLX
python -m venv .venv
.venv/bin/pip install git+https://github.com/ailuntx/mlx-audio.git
hf download mlx-community/MiMo-Audio-Tokenizer --local-dir ./models/MiMo-Audio-Tokenizer
hf download mlx-community/MiMo-V2.5-ASR-MLX-4bit --local-dir ./models/MiMo-V2.5-ASR-MLX-4bit
.venv/bin/python run_mimo_asr_mlx.py \
--model ./models/MiMo-V2.5-ASR-MLX-4bit \
--audio path/to/audio.wav
Variants
| Variant | Best for |
|---|---|
MiMo-V2.5-ASR-MLX |
default entry |
MiMo-V2.5-ASR-MLX-fp32 |
high-precision baseline |
MiMo-V2.5-ASR-MLX-bf16 |
high-quality Apple Silicon use |
MiMo-V2.5-ASR-MLX-8bit |
smaller local checkpoint |
MiMo-V2.5-ASR-MLX-4bit |
smallest checkpoint |
Layout
MiMo-V2.5-ASR-MLX-4bit/
βββ config.json
βββ model.safetensors / shards
βββ tokenizer files
βββ mlx_manifest.json
Conversion Notes
| Component | Source | MLX handling |
|---|---|---|
| ASR model | XiaomiMiMo/MiMo-V2.5-ASR |
converted to MLX weights |
| audio tokenizer | mlx-community/MiMo-Audio-Tokenizer |
downloaded separately and passed to the runtime |
| helper script | ailuntx/MiMo-V2.5-ASR-MLX |
wraps mlx-audio loading/generation |
Validation
Local Apple Silicon is the intended runtime. The HF Space can start and load the model on Linux CPU fallback, but full ASR on cpu-basic can exceed request timeouts.
License
License follows the upstream MiMo release.
Citation
@misc{mimo-v25-asr-mlx,
title = {MiMo-V2.5-ASR-MLX: Apple MLX port of MiMo-V2.5-ASR},
author = {ailuntx},
year = {2026},
url = {https://github.com/ailuntx/MiMo-V2.5-ASR-MLX},
}
@misc{xiaomi2026mimov25asr,
title = {MiMo-V2.5-ASR},
author = {{Xiaomi MiMo Team}},
year = {2026},
url = {https://github.com/XiaomiMiMo/MiMo-V2.5-ASR},
}