NVIDIA RTX 6000 Ada~245 tok/s (Q4)

deepseek-ai/DeepSeek-OCR speed on NVIDIA RTX 6000 Ada

Quantization-specific throughput and VRAM requirements for deepseek-ai/DeepSeek-OCR running on NVIDIA RTX 6000 Ada.

Speed Snapshot

Topline estimate from compatibility data

Modeldeepseek-ai/DeepSeek-OCR

GPUNVIDIA RTX 6000 Ada

Q4 speed245 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	48GB	245 tok/s	✅ Fits
Q8	4GB	48GB	145 tok/s	✅ Fits
FP16	7GB	48GB	91 tok/s	✅ Fits