NVIDIA RTX 6000 Ada~67 tok/s (Q4)

unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit speed on NVIDIA RTX 6000 Ada

Quantization-specific throughput and VRAM requirements for unsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit running on NVIDIA RTX 6000 Ada.

Speed Snapshot

Topline estimate from compatibility data

Modelunsloth/DeepSeek-R1-Distill-Qwen-32B-bnb-4bit

GPUNVIDIA RTX 6000 Ada

Q4 speed67 tok/s

Q4 VRAM required16GB

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	16GB	48GB	67 tok/s	✅ Fits
Q8	33GB	48GB	47 tok/s	✅ Fits
FP16	66GB	48GB	26 tok/s	❌ Not recommended