Can H200 141GB SXM5 run MiniMax-M2.7?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · MiniMax · 228.7B (active 10B) · MoE · model ctx up to 200K

Yes — the H200 141GB SXM5 (141 GB HBM3e) can run MiniMax-M2.7. At Q4 with the default 8K context it needs ≈ 128.79 GB VRAM (weights 125.79 GB + KV cache 2.0 GB + 1 GB runtime overhead), which fits within 141 GB. Decode at Q4/8K: ≈ 305.5 tok/s (estimated, batch 1). FP16 needs ≈ 460.4 GB — does not fit on this card. Estimates come from memory-bandwidth math; rows tagged measured override estimates. Relative ranking is more reliable than absolute tok/s. Methodology.

Fit & speed by quant and context

Quant	Context	VRAM needed	Fits?	tok/s (decode)
Q4	4K	127.79 GB	Yes	305.5 est.
Q4	8K default	128.79 GB	Yes	305.5 est.
Q4	32K	134.79 GB	No	955.0 est.
FP16	4K	459.4 GB	No	22.6 est.
FP16	8K default	460.4 GB	No	22.5 est.
FP16	32K	466.4 GB	No	21.9 est.

Fits = weights + KV(ctx) + 1 GB overhead ≤ 95% of VRAM. Measured anchors are context-agnostic; the fit verdict is recomputed per context. A missing tok/s means the model is far beyond this card (offload-only territory).

VRAM breakdown at 8K context

Quant	Weights	KV cache	Overhead	Total needed	H200 141GB SXM5 VRAM
Q4	125.79 GB	2.0 GB	1 GB	128.79 GB	141 GB
FP16	457.4 GB	2.0 GB	1 GB	460.4 GB	141 GB

Other GPUs that run MiniMax-M2.7

• B200 192GB SXM — ≈509.1 tok/s Q4 est.
• MI300X 192GB — ≈337.3 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈50.9 tok/s Q4 est.

All GPUs for MiniMax-M2.7 →

Other models for the H200 141GB SXM5

• Qwen3-0.6B — ≈3818.2 tok/s Q4 est.
• gemma-3-1b-it — ≈3054.5 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈2545.5 tok/s Q4 est.
• Qwen3-1.7B — ≈1527.3 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1018.2 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1018.2 tok/s Q4 est.
• GLM-4.7-Flash — ≈1018.2 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1018.2 tok/s Q4 est.

All models on the H200 141GB SXM5 →