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.
Lightweight option for
Mac X — on-device speech transcription on Apple Silicon via MLX with the smallest footprint.
Apache 2.0 — original model by
Mistral AI.
