NVIDIA H200 SXM 141GB~868 tok/s (Q4)

facebook/sam3 speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for facebook/sam3 running on NVIDIA H200 SXM 141GB.

Speed Snapshot

Topline estimate from compatibility data

Modelfacebook/sam3

GPUNVIDIA H200 SXM 141GB

Q4 speed868 tok/s

Q4 VRAM required1GB

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	1GB	141GB	868 tok/s	✅ Fits
Q8	1GB	141GB	528 tok/s	✅ Fits
FP16	2GB	141GB	332 tok/s	✅ Fits