MiniMax-M2.7

MiniMax · 228.7B (active 10B) · MoE · ctx 200K · MiniMax License · HuggingFace

MiniMax-M2.7 (MiniMax) is a 228.7B parameters MoE (10B active per token) open-weight model tracked on AI Hashrate. At 8K context we estimate roughly 128.79 GB VRAM for Q4 (weights 125.79 GB + KV 2.0 GB + 1 GB overhead) and 460.4 GB for FP16. About 4 GPUs/accelerators in our catalog fully fit this model at Q4 under that context assumption. Fastest Q4 configs: B200 192GB SXM ≈ 509.1 tok/s (estimated); MI300X 192GB ≈ 337.3 tok/s (estimated); H200 141GB SXM5 ≈ 305.5 tok/s (estimated); Mac Studio M2 Ultra 192GB ≈ 50.9 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.

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

Hardware	VRAM	Quant	tok/s	Fits?	tok/s/$
Gaudi 3 128GB	128	Q4	588.4 est.	No	0.047
B200 192GB SXM	192	Q4	509.1 est.	Yes	0.013
MI300X 192GB	192	Q4	337.3 est.	Yes	0.022
H200 141GB SXM5	141	Q4	305.5 est.	Yes	0.009
H100 80GB SXM5	80	Q4	235.0 est.	No	0.008
A100 80GB SXM4	80	Q4	143.0 est.	No	0.01
MacBook Pro M4 Max 128GB	128	Q4	98.1 est.	No	0.022
Mac Studio M3 Ultra 96GB	96	Q4	82.7 est.	No	0.021
MacBook Pro M3 Max 128GB	128	Q4	71.8 est.	No	0.017
B200 192GB SXM	192	FP16	69.6 est.	No	0.002
Mac Studio M2 Ultra 192GB	192	Q4	50.9 est.	Yes	0.007
MI300X 192GB	192	FP16	46.1 est.	No	0.003
RTX 6000 Ada 48GB	48	Q4	24.2 est.	No	0.004
H200 141GB SXM5	141	FP16	22.5 est.	No	0.001
L40S 48GB	48	Q4	21.8 est.	No	0.003
RTX A6000 48GB	48	Q4	19.4 est.	No	0.004
Gaudi 3 128GB	128	FP16	12.7 est.	No	0.001
Mac mini M4 Pro 64GB	64	Q4	12.3 est.	No	0.006
Mac Studio M2 Ultra 192GB	192	FP16	7.0 est.	No	0.001
MacBook Pro M4 Max 128GB	128	FP16	2.1 est.	No	0.0
MacBook Pro M3 Max 128GB	128	FP16	1.5 est.	No	0.0

Fit checks

• RTX 6000 Ada 48GB — does not fit · ≈24.2 tok/s Q4 est.
• L40S 48GB — does not fit · ≈21.8 tok/s Q4 est.
• Mac Studio M3 Ultra 96GB — does not fit · ≈82.7 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — fits · ≈50.9 tok/s Q4 est.

12 popular retail GPUs; every row in the table above also links its Fits? verdict to the full fit check.

Same family: MiniMax

MiniMax M3 MiniMax-M3

All MiniMax models →