Downloads · 30 days
14
6% of all-time downloads
Voxtral-Mini-4B-Realtime-2602-MLX-4bit
soloish90/Voxtral-Mini-4B-Realtime-2602-MLX-4bit
Voxtral-Mini-4B-Realtime-2602-MLX-4bit is a automatic speech recognition model from soloish90. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
This model shiny90/Voxtral-Mini-4B-Realtime-2602-MLX-4bit was converted to MLX format from mistralai/Voxtral-Mini-4B-Realtime-2602 using voxmlx.
All-time downloads
237
Public
Parameters
4.4B
2.5 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors2.5 GB · 99%
Parameter types
How the weights are stored.
U324.4B · 100%
Base models
Model card
From the Hugging Face model README
shiny90/Voxtral-Mini-4B-Realtime-2602-MLX-4bit
This model shiny90/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="shiny90/Voxtral-Mini-4B-Realtime-2602-MLX-4bit")
print(text)
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Languages
- en, fr, es, de, ru, zh
- Created
- Mar 8, 2026
- Updated
- Mar 8, 2026