Downloads · 30 days
22
14% of all-time downloads
Voxtral-Mini-3B-2507-MLX-FP16
aufklarer/Voxtral-Mini-3B-2507-MLX-FP16
Voxtral-Mini-3B-2507-MLX-FP16 is a automatic speech recognition model from aufklarer. Use it when you need speech turned into text. It is set up for mlx. The card lists the license as apache-2.0.
MLX weights for Voxtral Mini 3B 2507, ready for local speech-to-text with speech-swift.
All-time downloads
154
Public
Parameters
4.7B
9.4 GB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors9.4 GB · 100%
At a glance
- Task
- Automatic Speech Recognition
- Library
- mlx
- License
- apache-2.0
- Model type
- voxtral
- Access
- Public
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026
- SHA
- dfe9c4bb
Base models
Model card
From the Hugging Face model README
Voxtral Mini 3B 2507 — MLX FP16
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.
| Parameters | Precision | Sample rate | Languages |
|---|---|---|---|
| 3B | FP16 | 16 kHz | 8 |
Files
| File | Description |
|---|---|
model*.safetensors | MLX model weights |
config.json and params.json | Model and runtime configuration |
tekken.json | Tekken tokenizer data |
Usage
speech transcribe recording.wav --engine voxtral --model fp16
import VoxtralASR
let model = try await VoxtralModel.load(
"aufklarer/Voxtral-Mini-3B-2507-MLX-FP16"
)
let text = model.transcribe(
audio: samples,
sampleRate: sourceSampleRate,
language: "en"
)
Benchmark
English FLEURS read speech, 80 utterances (759.56 seconds), Apple M5 Pro:
| Variant | Bundle | WER | Mean RTF | Peak RSS |
|---|---|---|---|---|
| FP16 | 8.71 GiB | 4.633% | 0.1305 | 9,091 MiB |
| INT5 | 3.77 GiB | 4.744% | 0.0739 | 4,035 MiB |
| INT8 | 5.18 GiB | 4.578% | 0.0906 | 5,487 MiB |
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.
Links
- Task
- Automatic Speech Recognition
- Library
- mlx
- Type
- voxtral
- License
- apache-2.0
- Languages
- en, fr, de, es, it, pt
- Created
- Jul 23, 2026
- Updated
- Jul 23, 2026