Downloads · 30 days
22
26% of all-time downloads
voxtral-small-24b-2507
vokra/voxtral-small-24b-2507
voxtral-small-24b-2507 is a machine learning model from vokra. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for vokra. The card lists the license as apache-2.0.
Speech recognition model, converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.
All-time downloads
85
Public
Repo size
97.1 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.gguf48.5 GB · 100%
At a glance
- Library
- vokra
- License
- apache-2.0
- Access
- Public
- Created
- Jul 28, 2026
- Updated
- Aug 22, 2026
- SHA
- e4b91594
Model card
From the Hugging Face model README
voxtral-small-24b-2507 (Vokra GGUF)
Speech recognition model, converted to the Vokra GGUF format for Vokra, a zero-dependency speech-AI inference runtime.
This is a conversion, not a new model. The weights are the upstream ones; Vokra re-packages them so its runtime can memory-map them directly. Credit for the model belongs upstream — see Source below.
Files
| File | Size | SHA-256 |
|---|---|---|
model.gguf | 46293.6 MB | 91f2733492dd49b8e8f810192c77538d7d6d2f4c1c568098e11c3ad91f752c87 |
Usage
# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o model.gguf \
https://huggingface.co/vokra/voxtral-small-24b-2507/resolve/main/model.gguf
vokra-cli run --model model.gguf --input speech.wav
# Beam search instead of greedy
vokra-cli run --model model.gguf --input speech.wav --beam-size 5
Prints the transcript. Input must be mono 16 kHz WAV.
Provenance
| Field | Value |
|---|---|
| Architecture | voxtral |
| Tensors | 852 |
| Upstream source | mistralai/Voxtral-Small-24B-2507 (Apache-2.0) |
| Upstream licence | Apache-2.0 |
| Licence class | permissive |
| Registry model id | voxtral |
| Vokra GGUF schema | 1 |
| Converted by | vokra-core 0.1.0-alpha.0 |
Every row above is read out of this file's own vokra.* metadata, so the card cannot claim something the artifact does not carry.
Licence
The weights are distributed under Apache-2.0, unchanged from upstream. Conversion does not alter the licence, and your obligations run to the upstream author.
Verifying this file
shasum -a 256 model.gguf
# expect: 91f2733492dd49b8e8f810192c77538d7d6d2f4c1c568098e11c3ad91f752c87
- Library
- vokra
- License
- apache-2.0
- Created
- Jul 28, 2026
- Updated
- Aug 22, 2026