can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 4090 (24GB) run DeepSeek-R1-Distill 32B?

DeepSeek · Apache 2.0 · estimated for a 24.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 32B at Q3_K_M · 15.9 GB · 39–59 tok/s on a NVIDIA RTX 4090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB48–72 tok/sRuns great
Q3_K_M15.9 GB39–59 tok/sRuns great
Q4_K_M19.9 GB32–49 tok/sWon't fit
Q5_K_M23.3 GB28–42 tok/sWon't fit
Q6_K26.9 GB25–37 tok/sWon't fit
Q8_034.8 GB20–29 tok/sWon't fit
FP1665.5 GB11–16 tok/sWon't fit

Ran DeepSeek-R1-Distill 32B on a NVIDIA RTX 4090 (24GB)? Add your real numbers →