Can H200 141GB SXM5 run Qwen3-235B-A22B-Instruct-2507?

NVIDIA · 141 GB HBM3e · 4800 GB/s bandwidth · Alibaba · 235.1B (active 22B) · MoE · model ctx up to 256K

Partly — Qwen3-235B-A22B-Instruct-2507 at Q4 fits the H200 141GB SXM5 (141 GB HBM3e) at 4K context (≈ 132.5 GB) but not at the default 8K (≈ 134.71 GB needed). Use a shorter context or partial offload. Decode at Q4/8K: ≈ 434.6 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	138.8 est.
Q4	8K default	134.71 GB	No	434.6 est.
Q4	32K	147.91 GB	No	360.5 est.
FP16	4K	473.4 GB	No	9.7 est.
FP16	8K default	475.6 GB	No	9.6 est.
FP16	32K	488.8 GB	No	9.1 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	H200 141GB SXM5 VRAM
Q4	129.31 GB	4.4 GB	1 GB	134.71 GB	141 GB
FP16	470.2 GB	4.4 GB	1 GB	475.6 GB	141 GB

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

• B200 192GB SXM — ≈231.4 tok/s Q4 est.
• 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 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 →