Voxtral Mini 4B Realtime
Hugging Face (open weights) Open weights
The catch: Transcription only, in 13 languages.
| Access | Open weights |
|---|---|
| Free limits | Free to download and self-host; you pay only for your own compute. 4B real-time speech transcription for 13 languages with under 500ms delay; built for on-device use. Apache 2.0. |
| Modality | audio |
| Credit card | Not required |
| Commercial use | Allowed |
| Trains on your data | – |
| Licence or terms | Apache-2.0 |
| Context window | 131,072 tokens |
| Model id | mistralai/Voxtral-Mini-4B-Realtime-2602 |
| Base URL | – |
| Last checked | 8 Oct 2026 |
How to use Voxtral Mini 4B Realtime
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Quickstart
uv pip install -U vllm && VLLM_DISABLE_COMPILE_CACHE=1 vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602 --compilation_config '{"cudagraph_mode": "PIECEWISE"}'Paste into Claude Code
I want to run the open-weight model "Voxtral Mini 4B Realtime" (mistralai/Voxtral-Mini-4B-Realtime-2602) for my project. Please: 1. Check the model card and tell me the hardware it needs and the simplest way to serve it (vLLM, SGLang, Ollama or a hosted endpoint). 2. Give me a minimal working setup and a test request. 3. Tell me the licence terms for commercial use. 4. If a cheaper or smaller variant would do the job, mention it.
Before you ship on it
- Transcription only, in 13 languages.
- Apache-2.0 (licence tag on the HF repo): use, modify, distribute and sell, including commercially; keep the licence and notices when you redistribute.
- Free to run means you pay for the GPUs, the serving stack and the on-call.
Questions
Is Voxtral Mini 4B Realtime free?
Yes. Open weights offers it as open weights, with these limits: Self-host free · Apache-2.0. No credit card is needed.
Can I use Voxtral Mini 4B Realtime commercially?
Yes, under Apache-2.0. Check the current terms before you ship.
How do I start with Voxtral Mini 4B Realtime?
Download the weights and serve them yourself; the quickstart below shows one way. Licence: Apache-2.0.
Source: huggingface.co/mistralai/Voxtral-Mini-4B-Realtime-2602, checked 8 Oct 2026.