NVIDIA H200 SXM 141GB~814 tok/s (Q4)

meta-llama/Llama-3.2-3B speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for meta-llama/Llama-3.2-3B running on NVIDIA H200 SXM 141GB.

Speed Snapshot

Topline estimate from compatibility data

Modelmeta-llama/Llama-3.2-3B

GPUNVIDIA H200 SXM 141GB

Q4 speed814 tok/s

Q4 VRAM required2GB

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	2GB	141GB	814 tok/s	✅ Fits
Q8	3GB	141GB	555 tok/s	✅ Fits
FP16	6GB	141GB	319 tok/s	✅ Fits