can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5070 (12GB) run DeepSeek-R1-Distill 14B?

DeepSeek · Apache 2.0 · estimated for a 12.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 14B at Q3_K_M · 7.3 GB · 52–78 tok/s on a NVIDIA RTX 5070 (12GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB63–94 tok/sRuns great
Q3_K_M7.3 GB52–78 tok/sRuns great
Q4_K_M9.0 GB45–67 tok/sTight / slow
Q5_K_M10.5 GB39–59 tok/sWon't fit
Q6_K12.1 GB35–52 tok/sWon't fit
Q8_015.7 GB28–42 tok/sWon't fit
FP1629.6 GB16–23 tok/sWon't fit

Ran DeepSeek-R1-Distill 14B on a NVIDIA RTX 5070 (12GB)? Add your real numbers →