What GPU do I need to run mistral-experimental/pixtral-12b?
12.7B parameters, published in BF16. View on Hugging Face
Set up pixtral-12bpixtral-12b is published by mistral-experimental on Hugging Face, with 138,105 downloads and 106 likes to date. It's a LlavaForConditionalGeneration model built for image-text-to-text, published natively in BF16.
VRAM required & cheapest live GPU fit
Required VRAM = weight size at each precision, plus a fixed overhead for KV-cache, activations, and fragmentation. Full formula and assumptions: methodology.
| Precision | Weight size | Required VRAM | Cheapest live fit | GPUs needed | Est. $/hr (full fit) |
|---|---|---|---|---|---|
| BF16 | 23.6 GB | 28.3 GB | RTX 4080 Super | 1 | $0.338/hr |
| cheaper alt. | RTX 5060 Ti | 2 | $0.220/hr | ||
| FP8 (quantized) | 11.8 GB | 14.2 GB | RTX 5060 Ti | 1 | $0.110/hr |
| INT4 (quantized) | 5.9 GB | 7.1 GB | RTX 5060 Ti | 1 | $0.110/hr |
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 requires a quantized checkpoint actually published for this model, check its Hugging Face page before relying on this row.
Cheapest way to run pixtral-12b at its published (BF16) precision: 1× RTX 4080 Super, at $0.338/hr per GPU ($0.338/hr total). Quantizing to FP8 or INT4 (rows above) can cost less, but requires a compatible quantized checkpoint to exist for this model.
pixtral-12b: common questions
Does pixtral-12b fit on a 32 GB GPU?
Yes. At BF16 it needs 28.3 GB of VRAM, so a 32 GB card holds it with 3.7 GB to spare. A 24 GB card is not enough for it at BF16.
What is the least VRAM pixtral-12b can run in?
7.1 GB, at INT4 (quantized), which fits an 8 GB card, against 28.3 GB at BF16. That row assumes an INT4 checkpoint has actually been published for this model, so check its Hugging Face page before planning around it.
Does quantizing pixtral-12b lower the GPU bill?
Yes. At BF16 the cheapest live fit is one RTX 4080 Super at $0.338/hr. At FP8 (quantized) it drops to one RTX 5060 Ti at $0.110/hr, provided a quantized checkpoint exists for it.
Weight-to-VRAM math, the fit rules, and how live prices are normalized: full methodology.
Related reading: H100 pricing and specs, The best GPUs for AI, ranked, and Best GPU for LLM inference.
