Safetensors
MLX
mlx-audio
voxtral_realtime
speech-to-text
speech
transcription
asr
stt
4-bit precision
Instructions to use shreyask/voxtral-mini-4b-realtime-mlx-mixed-4-6 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use shreyask/voxtral-mini-4b-realtime-mlx-mixed-4-6 with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] hf download shreyask/voxtral-mini-4b-realtime-mlx-mixed-4-6 --local-dir voxtral-mini-4b-realtime-mlx-mixed-4-6
- Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- LM Studio
- Atomic Chat
Ctrl+K