What GPU do I need to run MiniMaxAI/MiniMax-M3-MXFP8?
440.3B parameters, published in F8_E4M3. View on Hugging Face
MiniMax-M3-MXFP8 is published by MiniMaxAI on Hugging Face, with 366,068 downloads and 55 likes to date. It's a MiniMaxM3SparseForConditionalGeneration model built for image-text-to-text, published natively in F8_E4M3.
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.
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 MiniMax-M3-MXFP8 at its published (F8_E4M3) precision: 6× RTX PRO 6000 on runpod, at $1.69/hr per GPU ($10.14/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 MiniMaxAI models
- MiniMax-H3 (33.1B, BF16)
- MiniMax-M2.7 (228.7B, F8_E4M3)
- MiniMax-M2.5 (228.7B, F8_E4M3)
- MiniMax-M2 (228.7B, F8_E4M3)
- MiniMax-M3 (427.0B, BF16)
- MiniMax-M2.1 (228.7B, F8_E4M3)
