Running Voxtral-Mini-3B-2507 on GPU requires ~9.5 GB of GPU RAM in bf16 or fp16.

Running Voxtral-Small-24B-2507 on GPU requires ~55 GB of GPU RAM in bf16 or fp16.

Im pretty excited to play around with this. I’ve worked with whisper quite a bit, it’s awesome to have another model in the same class and from Mistral, who tend to be very open. I’m sure unsloth is already working on some GGUF quants - will probably spin it up tomorrow and try it on some audio.

24B is crazy expensive for speech transcription. Conspicuously no comparison with Parakeet, a 600M param model thats currently dominating leaderboards (but only for English)

In demo they mention polish prononcuation is pretty bad, spoken as if second language of english-native speaker. I wonder if it's the same for other languages. On the other hand whispering-english is hillariously good, especially different emotions.

There is also a Voxtral Small 24B small model available to be downloaded: https://huggingface.co/mistralai/Voxtral-Small-24B-2507

Does it support realtime transcription? What is the ~latency?

weights:https://huggingface.co/mistralai/Voxtral-Mini-3B-2507 and https://huggingface.co/mistralai/Voxtral-Small-24B-2507

They claim to undercut competitors of similar quality by half for both models, yet they released both as Apache 2.0 instead of following smaller - open, larger - closed strategy used for their last releases. What's different here?

My Whisper v3 Large Turbo is $0.001/min, so their price comparison is not exactly perfect.