Voxtral-Mini-4B-Realtime-2602
Will it run on your hardware?
Pick your GPU memory - see which quantizations fit, and the cheapest card for the rest
Need an exact figure for your context length? Use the VRAM calculator.
Run it locally
Copy-paste - running in under a minute
vllm serve mistralai/Voxtral-Mini-4B-Realtime-2602New to this? Start with Ollama · serve to many users with vLLM.
Deep dive
Notes, sources, and the full write-up
Voxtral-Mini-4B-Realtime-2602 is an open-weight speech recognition model from mistralai, published on Hugging Face in January 2026. It has 4.4B parameters and is released under the apache-2.0 license.
HardwareLink to this section
At full FP16 precision the weights need about 9 GB of memory; 8-bit quantization brings that to roughly 5 GB. Check the VRAM tiers above to see which GPUs fit it.
PopularityLink to this section
Voxtral-Mini-4B-Realtime-2602 had 1,520,221 downloads on Hugging Face in the last month and has 1,061 likes.
Run it locallyLink to this section
The weights are on Hugging Face and load with vllm. Follow the model card for the exact setup and license terms.
Frequently asked
Quick answers to common questions
How much VRAM does Voxtral-Mini-4B-Realtime-2602 need?
Voxtral-Mini-4B-Realtime-2602 with 4.4B parameters needs approximately 3 GB at Q4_K_M quantization. Use our VRAM calculator for an exact estimate.
Is Voxtral-Mini-4B-Realtime-2602 better than other mistralai models?
Voxtral-Mini-4B-Realtime-2602 has 4.4B parameters with 131,072 context - a strong choice for speech-recognition.
What license is Voxtral-Mini-4B-Realtime-2602 under?
Voxtral-Mini-4B-Realtime-2602 is released under the apache-2.0 license, making it suitable for most commercial and personal projects.
What hardware runs Voxtral-Mini-4B-Realtime-2602 well?
With 4.4B parameters, Voxtral-Mini-4B-Realtime-2602 requires adequate VRAM. High-end GPUs like the RTX 4090 (24GB), RTX 5090 (32GB), or Mac Studio with unified memory are good options. Check our hardware directory for specific recommendations.
What is the best quantization for Voxtral-Mini-4B-Realtime-2602?
Q4_K_M is the recommended sweet spot - ~98% of FP16 quality at ~27% of the size. Q5_K_M (~3 GB) is an option if you have spare VRAM. Use our VRAM calculator to compare.
How long can Voxtral-Mini-4B-Realtime-2602's context window handle?
Voxtral-Mini-4B-Realtime-2602 supports a 131,072-token context window - enough for very long documents, codebases, or multi-turn conversations. Real-world usable context may vary by implementation.
What models compete with Voxtral-Mini-4B-Realtime-2602?
Voxtral-Mini-4B-Realtime-2602 competes with other models in its class. Browse our model directory for comparisons, benchmarks, and community reviews to find the best fit.
Nearby options
Similar models and compatible hardware by spec