voxtral-mini-4b-realtime-2602 (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	8449.0 MB	2d534be6333dac4e76d94c59906b2193fb9dfd0d22779190625f4c356304a641

Usage

# Download (any HTTP client works — the file is a plain GGUF)
curl -L -o model.gguf \
  https://huggingface.co/vokra/voxtral-mini-4b-realtime-2602/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	711
Upstream source	mistralai/Voxtral-Mini-3B (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: 2d534be6333dac4e76d94c59906b2193fb9dfd0d22779190625f4c356304a641