NVIDIA H200 SXM 141GB~372 tok/s (Q4)

Qwen/Qwen3-30B-A3B-Thinking-2507 speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for Qwen/Qwen3-30B-A3B-Thinking-2507 running on NVIDIA H200 SXM 141GB.

Speed Snapshot

Topline estimate from compatibility data

ModelQwen/Qwen3-30B-A3B-Thinking-2507

GPUNVIDIA H200 SXM 141GB

Q4 speed372 tok/s

Q4 VRAM required15GB

Data Source

Calculation and benchmark status

Speed values come from the compatibility dataset (`estimatedTokensPerSec`) and are sorted by quantization.

For full verdict logic and alternate GPUs, see the canonical compatibility page.

Quantization Speed Table

Quantization	VRAM needed	VRAM available	Speed	Verdict
Q4	15GB	141GB	372 tok/s	✅ Fits
Q8	31GB	141GB	258 tok/s	✅ Fits
FP16	61GB	141GB	150 tok/s	✅ Fits