NVIDIA H200 SXM 141GB~125 tok/s (Q4)

openai/gpt-oss-120b speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for openai/gpt-oss-120b running on NVIDIA H200 SXM 141GB.

Speed Snapshot

Topline estimate from compatibility data

Modelopenai/gpt-oss-120b

GPUNVIDIA H200 SXM 141GB

Q4 speed125 tok/s

Q4 VRAM required59GB

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	59GB	141GB	125 tok/s	✅ Fits
Q8	117GB	141GB	104 tok/s	✅ Fits
FP16	235GB	141GB	47 tok/s	❌ Not recommended