aufklarer/Voxtral-Mini-3B-2507-MLX-5bit
040
Voxtral Mini 3B 2507 — MLX 5-bit affine
MLX weights for Voxtral Mini 3B 2507, ready for local speech-to-text with speech-swift.
The FP16, INT5, and INT8 family passed the isolated WER, RTF, throughput, RSS, and physical-footprint compatibility gate on 2026-07-22 using English FLEURS.
Files
Usage
speech transcribe recording.wav --engine voxtral --model int5import VoxtralASR
let model = try await VoxtralModel.load(
"aufklarer/Voxtral-Mini-3B-2507-MLX-5bit"
)
let text = model.transcribe(
audio: samples,
sampleRate: sourceSampleRate,
language: "en"
)Benchmark
English FLEURS read speech, 80 utterances (759.56 seconds), Apple M5 Pro:
These read-speech measurements are not Artificial Analysis Conversational or ElevenLabs Scribe results.
Source and license
The base model is mistralai/Voxtral-Mini-3B-2507 and is released under Apache 2.0.
