NVIDIA RTX 6000 Ada~139 tok/s (Q4)

ai-forever/ruGPT-3.5-13B speed on NVIDIA RTX 6000 Ada

Quantization-specific throughput and VRAM requirements for ai-forever/ruGPT-3.5-13B running on NVIDIA RTX 6000 Ada.

Speed Snapshot

Topline estimate from compatibility data

Modelai-forever/ruGPT-3.5-13B

GPUNVIDIA RTX 6000 Ada

Q4 speed139 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	48GB	139 tok/s	✅ Fits
Q8	13GB	48GB	92 tok/s	✅ Fits
FP16	27GB	48GB	48 tok/s	✅ Fits