can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run DeepSeek-R1-Distill 32B?

DeepSeek · Apache 2.0 · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: DeepSeek-R1-Distill 32B at FP16 · 65.5 GB · 46–70 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K12.3 GB154–231 tok/sRuns great
Q3_K_M15.9 GB133–199 tok/sRuns great
Q4_K_M19.9 GB116–174 tok/sRuns great
Q5_K_M23.3 GB104–156 tok/sRuns great
Q6_K26.9 GB94–141 tok/sRuns great
Q8_034.8 GB78–117 tok/sRuns great
FP1665.5 GB46–70 tok/sRuns great

Ran DeepSeek-R1-Distill 32B on a NVIDIA H200 (141GB)? Add your real numbers →