Voxtral Mini 3B (MLX, 4-bit mixed)
4-bit mixed quantized MLX weights for Mistral's Voxtral Mini speech-to-text model, optimized for Apple Silicon inference. Smallest download size with slightly reduced quality.
Voxtral Mini is built on Ministral 3B with state-of-the-art audio understanding capabilities. It supports transcription, translation, Q&A, summarization, and function calling directly from audio input.
Features
- 8 languages: English, Spanish, French, Portuguese, Hindi, German, Dutch, Italian
- Long-form audio: up to 30 min transcription, 40 min understanding
- 32k token context
- Voice-triggered function calling
Specifications
| Property | Value |
|---|---|
| Total Parameters | 4.68B (4-bit mixed quantized) |
| Precision | 4-bit mixed |
| Download Size | 3.2 GB |
| License | Apache 2.0 |
Usage
Lightweight option for Mac X — on-device speech transcription on Apple Silicon via MLX with the smallest footprint.
See also: Full precision (bfloat16) (17.4 GB) | 8-bit quantized (5 GB)
License
Apache 2.0 — original model by Mistral AI.
- Downloads last month
- 6
Model size
0.9B params
Tensor type
F16
·
U32 ·
BF16 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for Aayush9029/voxtral-mini-3b-4bit-mixed
Base model
mistralai/Voxtral-Mini-3B-2507