can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5070 Ti (16GB) run DeepSeek-R1-Distill 32B?

DeepSeek · Apache 2.0 · estimated for a 16.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: DeepSeek-R1-Distill 32B at Q2_K · 12.3 GB · 44–65 tok/s on a NVIDIA RTX 5070 Ti (16GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB44–65 tok/sTight / slow
Q3_K_M15.9 GB35–53 tok/sWon't fit
Q4_K_M19.9 GB29–44 tok/sWon't fit
Q5_K_M23.3 GB25–38 tok/sWon't fit
Q6_K26.9 GB22–33 tok/sWon't fit
Q8_034.8 GB18–26 tok/sWon't fit
FP1665.5 GB10–15 tok/sWon't fit

Ran DeepSeek-R1-Distill 32B on a NVIDIA RTX 5070 Ti (16GB)? Add your real numbers →