Can B200 192GB SXM run MiMo-V2.5?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Xiaomi · 310.0B (active 15.0B) · MoE · model ctx up to 1024K

Yes — the B200 192GB SXM (192 GB HBM3e) can run MiMo-V2.5. At Q4 with the default 8K context it needs ≈ 174.5 GB VRAM (weights 170.5 GB + KV cache 3.0 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 339.4 tok/s (estimated, batch 1). FP16 needs ≈ 624.0 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	173.0 GB	Yes	339.4 est.
Q4	8K default	174.5 GB	Yes	339.4 est.
Q4	32K	183.5 GB	No	1061.6 est.
FP16	4K	622.5 GB	No	25.4 est.
FP16	8K default	624.0 GB	No	25.2 est.
FP16	32K	633.0 GB	No	24.5 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	B200 192GB SXM VRAM
Q4	170.5 GB	3.0 GB	1 GB	174.5 GB	192 GB
FP16	620.0 GB	3.0 GB	1 GB	624.0 GB	192 GB

Other GPUs that run MiMo-V2.5

• MI300X 192GB — ≈224.8 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈33.9 tok/s Q4 est.

All GPUs for MiMo-V2.5 →

Other models for the B200 192GB SXM

• MiniCPM5-1B — ≈4713.8 tok/s Q4 est.
• Qwen3.5-2B — ≈2545.5 tok/s Q4 est.
• GLM-4.7-Flash — ≈1697.0 tok/s Q4 est.
• Qwen3-30B-A3B-Instruct-2507 — ≈1697.0 tok/s Q4 est.
• Qwen3-Next-80B-A3B-Instruct — ≈1697.0 tok/s Q4 est.
• Qwen3-Coder-Next — ≈1697.0 tok/s Q4 est.
• Qwen3.5-35B-A3B — ≈1697.0 tok/s Q4 est.
• Qwen3.6-35B-A3B — ≈1697.0 tok/s Q4 est.

All models on the B200 192GB SXM →