Instructions to use schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- MLX
How to use schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit with MLX:
# Download the model from the Hub pip install huggingface_hub[hf_xet] huggingface-cli download --local-dir Voxtral-Mini-4B-Realtime-2602-MLX-4bit schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit
- Notebooks
- Google Colab
- Kaggle
- Local Apps
- LM Studio
schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit
This model schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit was converted to MLX format from mistralai/Voxtral-Mini-4B-Realtime-2602 using voxmlx.
Use with voxmlx
pip install voxmlx
from voxmlx import transcribe
text = transcribe("audio.flac", model_path="schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit")
print(text)
- Downloads last month
- 48
Model size
0.7B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
Quantized
Model tree for schroneko/Voxtral-Mini-4B-Realtime-2602-MLX-4bit
Base model
mistralai/Ministral-3-3B-Base-2512 Finetuned
mistralai/Voxtral-Mini-4B-Realtime-2602