Can B200 192GB SXM run Qwen3-235B-A22B-Instruct-2507?

NVIDIA · 192 GB HBM3e · 8000 GB/s bandwidth · Alibaba · 235.1B (active 22B) · MoE · model ctx up to 256K

Yes — the B200 192GB SXM (192 GB HBM3e) can run Qwen3-235B-A22B-Instruct-2507. At Q4 with the default 8K context it needs ≈ 134.71 GB VRAM (weights 129.31 GB + KV cache 4.4 GB + 1 GB runtime overhead), which fits within 192 GB. Decode at Q4/8K: ≈ 231.4 tok/s (estimated, batch 1). FP16 needs ≈ 475.6 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	132.5 GB	Yes	231.4 est.
Q4	8K default	134.71 GB	Yes	231.4 est.
Q4	32K	147.91 GB	Yes	231.4 est.
FP16	4K	473.4 GB	No	29.9 est.
FP16	8K default	475.6 GB	No	29.6 est.
FP16	32K	488.8 GB	No	28.1 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	129.31 GB	4.4 GB	1 GB	134.71 GB	192 GB
FP16	470.2 GB	4.4 GB	1 GB	475.6 GB	192 GB

Other GPUs that run Qwen3-235B-A22B-Instruct-2507

• MI300X 192GB — ≈153.3 tok/s Q4 est.
• Mac Studio M2 Ultra 192GB — ≈23.1 tok/s Q4 est.

All GPUs for Qwen3-235B-A22B-Instruct-2507 →

Other models for the B200 192GB SXM

• gemma-3-1b-it — ≈5000 tok/s Q4 est.
• Qwen3-0.6B — ≈5000 tok/s Q4 est.
• Llama-3.2-1B-Instruct — ≈4242.4 tok/s Q4 est.
• Qwen3-1.7B — ≈2545.5 tok/s Q4 est.
• Qwen3-30B-A3B — ≈1697.0 tok/s Q4 est.
• Qwen3-Coder-30B-A3B-Instruct — ≈1697.0 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.

All models on the B200 192GB SXM →