What GPU do I need to run mistralai/Voxtral-Mini-4B-Realtime-2602?
4.4B parameters, published in BF16. View on Hugging Face
Voxtral-Mini-4B-Realtime-2602 is published by mistralai on Hugging Face, with 2,336,250 downloads and 949 likes to date. It's a VoxtralRealtimeForConditionalGeneration model built for automatic-speech-recognition, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for activations and allocator fragmentation. Speech models don't build the same growing KV-cache a text model does — memory scales primarily with input audio length. Full formula and assumptions: methodology.
A GPU is only matched to a row if its hardware supports that precision, and the primary recommendation is always a single-GPU fit when one exists.
INT4 caveat: requires a quantized checkpoint actually published for this model — check its Hugging Face page before relying on this row.
Cheapest way to run Voxtral-Mini-4B-Realtime-2602 at its published (BF16) precision: 1× RTX 3060 on simplepod, at $0.070/hr per GPU ($0.070/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
More mistralai models
- Mistral-7B-Instruct-v0.2 (7.2B, BF16)
- Mistral-7B-v0.1 (7.2B, BF16)
- Mistral-7B-Instruct-v0.1 (7.2B, BF16)
- Qwen3-0.6B (752M, BF16)
- Qwen3-8B (8.2B, BF16)
- gpt2 (137M, F32)
