Automatic Speech Recognition
MLX
Safetensors
voxtral
audio
speech
speech-recognition
transcription
translation
rotorquant
quantization
4-bit precision
Instructions to use majentik/Voxtral-Mini-3B-2507-RotorQuant-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use majentik/Voxtral-Mini-3B-2507-RotorQuant-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Voxtral-Mini-3B-2507-RotorQuant-MLX-4bit majentik/Voxtral-Mini-3B-2507-RotorQuant-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Xet hash:
- 52c4cdbc596882d110d7002d0664dc3af135b1eb010a2482ba3c568d43256061
- Size of remote file:
- 1.41 GB
- SHA256:
- 320760cb856b3bf0ffa219ba9c289e4b2a73b04f48c52c13658a5e6637aa914d
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.