Voxtral Mini 4B Realtime 2602
Mistral's Voxtral Mini 4B Realtime 2602 is a multilingual, realtime speech-transcription model, capable of achieving accuracy comparable to offline systems. It is genuinely best at providing low-latency transcription with a recommended delay of 480ms, striking a balance between performance and latency.
Input
Output
Context
131K
Max Output
-
Parameters
4.4B
Technical Specifications
Model TypeAudio
Context Window131,072 tokens
Max Output TokensNot available
Parameters4.4B
Release DateJan 21, 2026
Training CutoffNot available
Licenseapache-2.0
Open SourceYes
Input Modalities
Audio
Output Modalities
Text
Capabilities
Estimated GPU Requirements for Voxtral Mini 4B Realtime 2602
Estimates based on INT8 quantization. Actual requirements vary by framework and configuration.
More Models by Mistral
Voxtral Mini Realtime Charente 2606 Solutions33K context · Open weightsLabs Leanstral 1.5.1262K context · Open weightsMistral Small 2506131K context · Open weightsMagistral Small 2509131K context · 24B · Open weightsMinistral 3 8B Instruct 2512 BF16262K context · 8.9B · Open weightsMistral 7B Instruct V0.233K context · 7.2B · Open weights
Related Tools
Data sourced from official provider APIs and documentation
Last updated: Aug 8, 2026
Your AI stack shouldn't stand still.
Every month new models become cheaper, faster, and more capable. Inferbase ensures your application automatically benefits without changing a single API call.