can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA L40S (48GB) run DeepSeek-R1-Distill 14B?

DeepSeek · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 14B at FP16 · 29.6 GB · 20–30 tok/s on a NVIDIA L40S (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K5.8 GB77–115 tok/sRuns great
Q3_K_M7.3 GB65–97 tok/sRuns great
Q4_K_M9.0 GB55–83 tok/sRuns great
Q5_K_M10.5 GB49–73 tok/sRuns great
Q6_K12.1 GB44–65 tok/sRuns great
Q8_015.7 GB35–52 tok/sRuns great
FP1629.6 GB20–30 tok/sRuns great

Ran DeepSeek-R1-Distill 14B on a NVIDIA L40S (48GB)? Add your real numbers →