handy-computer / automatic-speech-recognition updated 1 month ago

Voxtral-Mini-4B-Realtime-2602-gguf

GGUF conversions of mistralai/Voxtral-Mini-4B-Realtime-2602 for use with transcribe.cpp.

Params
Context
Downloads 30d
430 K
Likes
1
Commercial use: allowed apache-2.0 Not gated GGUF 13 languages View on Hugging Face ↗

Download history

daily snapshots · 10 days
431 K401 K
Jul 28Jul 31Aug 3Aug 6

Can you run it?

Estimated VRAM at 8K context unless noted. Pick your hardware to see the verdict per quantization.

FileQuantSizeEst. VRAMVerdict on RTX 4090 · 24 GB
Voxtral-Mini-4B-Realtime-2602-Q4_K_M.gguf Q4_K_M 2.8 GB 3.6 GB ✅ Runs comfortably
Voxtral-Mini-4B-Realtime-2602-Q5_K_M.gguf Q5_K_M 3.3 GB 4.1 GB ✅ Runs comfortably
Voxtral-Mini-4B-Realtime-2602-Q6_K.gguf Q6_K 3.7 GB 4.5 GB ✅ Runs comfortably
Voxtral-Mini-4B-Realtime-2602-Q8_0.gguf Q8_0 4.7 GB 5.7 GB ✅ Runs comfortably
Voxtral-Mini-4B-Realtime-2602-F16.gguf GGUF 8.9 GB 10.3 GB ✅ Runs comfortably
Estimate: file size × 1.1 + KV cache at 8K + 0.5 GB overhead. Not a benchmark — how we calculate this.

Specifications

Licence
apache-2.0
First seen on the Hub
2026-06-05
Base model
Voxtral-Mini-4B-Realtime-2602
Training datasets
undisclosed
Added to our catalog
2026-07-28

Family

Base model and the most-downloaded derivatives in the catalog.