Can MI300X 192GB run MiniMax-M2.7?

AMD · 192 GB HBM3 · 5300 GB/s bandwidth · MiniMax · 228.7B (active 10B) · MoE · model ctx up to 200K

Yes — the MI300X 192GB (192 GB HBM3) 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 192 GB. Decode at Q4/8K: ≈ 337.3 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	337.3 est.
Q4	8K default	128.79 GB	Yes	337.3 est.
Q4	32K	134.79 GB	Yes	337.3 est.
FP16	4K	459.4 GB	No	46.3 est.
FP16	8K default	460.4 GB	No	46.1 est.
FP16	32K	466.4 GB	No	44.9 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	MI300X 192GB VRAM
Q4	125.79 GB	2.0 GB	1 GB	128.79 GB	192 GB
FP16	457.4 GB	2.0 GB	1 GB	460.4 GB	192 GB

Other GPUs that run MiniMax-M2.7

• B200 192GB SXM — ≈509.1 tok/s Q4 est.
• H200 141GB SXM5 — ≈305.5 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 MI300X 192GB

• Qwen3-0.6B — ≈4215.9 tok/s Q4 est.
• gemma-3-1b-it — ≈3372.7 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈2810.6 tok/s Q4 est.
• Qwen3-1.7B — ≈1686.4 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1124.2 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1124.2 tok/s Q4 est.
• GLM-4.7-Flash — ≈1124.2 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1124.2 tok/s Q4 est.

All models on the MI300X 192GB →