NVIDIA H200 SXM 141GB~473 tok/s (Q4)

ai-forever/ruGPT-3.5-13B speed on NVIDIA H200 SXM 141GB

Quantization-specific throughput and VRAM requirements for ai-forever/ruGPT-3.5-13B running on NVIDIA H200 SXM 141GB.

Speed Snapshot

Topline estimate from compatibility data

Modelai-forever/ruGPT-3.5-13B

GPUNVIDIA H200 SXM 141GB

Q4 speed473 tok/s

Q4 VRAM required7GB

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	7GB	141GB	473 tok/s	✅ Fits
Q8	13GB	141GB	349 tok/s	✅ Fits
FP16	27GB	141GB	196 tok/s	✅ Fits