MiniMax-M1 — which GPUs fit

MiniMax · 456.1B (active 45.9B) · MoE · ctx 1000K · apache-2.0 · HuggingFace

MiniMax-M1 (MiniMax) is a 456.1B parameters MoE (45.9B active per token) open-weight model tracked on AI Hashrate. At 8K context we estimate roughly 261.04 GB VRAM for Q4 (weights 250.86 GB + KV 9.18 GB + 1 GB overhead) and 922.38 GB for FP16. About 0 GPUs/accelerators in our catalog fully fit this model at Q4 under that context assumption. Fastest Q4 configs: B200 192GB SXM ≈ 171.4 tok/s (estimated); MI300X 192GB ≈ 113.6 tok/s (estimated); H200 141GB SXM5 ≈ 55.5 tok/s (estimated). Use the table below for VRAM fit and tok/s per dollar (list MSRP). Estimates follow memory-bandwidth math; measured rows override when present. See methodology for details. Methodology.

10 hardware configs — sorted by tok/s. Default fit context 8K.

Hardware	VRAM	Quant	tok/s	Fits?	tok/s/$
B200 192GB SXM	192	Q4	171.4 est.	No	0.004
MI300X 192GB	192	Q4	113.6 est.	No	0.008
H200 141GB SXM5	141	Q4	55.5 est.	No	0.002
Gaudi 3 128GB	128	Q4	31.2 est.	No	0.002
Mac Studio M2 Ultra 192GB	192	Q4	17.1 est.	No	0.002
H100 80GB SXM5	80	Q4	12.5 est.	No	0.0
A100 80GB SXM4	80	Q4	7.6 est.	No	0.001
MacBook Pro M4 Max 128GB	128	Q4	5.2 est.	No	0.001
Mac Studio M3 Ultra 96GB	96	Q4	4.4 est.	No	0.001
MacBook Pro M3 Max 128GB	128	Q4	3.8 est.	No	0.001