---
library_name: mlx
base_model: mistralai/Voxtral-Mini-4B-Realtime-2602
tags:
  - mlx
  - speech-to-text
  - audio
  - realtime
  - voxtral
  - quantized
  - 8bit
license: apache-2.0
pipeline_tag: automatic-speech-recognition
---

# Voxtral Mini 4B Realtime - 8-bit MLX

This is an 8-bit quantized [MLX](https://github.com/ml-explore/mlx) version of [Voxtral Mini 4B Realtime](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602) by Mistral AI, converted using [voxmlx](https://github.com/awni/voxmlx).

This version was created for use with [Supervoxtral](https://github.com/jphme/supervoxtral), enabling blazingly-fast realtime transcription on MacOS.

## Model Details

- **Base model:** [mistralai/Voxtral-Mini-4B-Realtime-2602](https://huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602)
- **Quantization:** 8-bit (group size 64)
- **Framework:** MLX
- **Parameters:** ~4B (3.4B language model + 970M audio encoder)
- **License:** Apache 2.0

## Description

Voxtral Mini is a speech-to-text model that supports 13+ languages with sub-500ms latency. This version has been quantized to 8-bit precision for efficient inference on Apple Silicon using the MLX framework.


## Credits

- Original model by [Mistral AI](https://mistral.ai/)
- MLX conversion tooling by [voxmlx](https://github.com/awni/voxmlx)