can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA H200 (141GB) run Llama 3.2 1B?

Llama · Llama 3.2 Community · estimated for a 141.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.2 1B at FP16 · 2.5 GB · 289–433 tok/s on a NVIDIA H200 (141GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M0.8 GB336–504 tok/sRuns great
Q5_K_M0.9 GB332–498 tok/sRuns great
Q6_K1.0 GB328–492 tok/sRuns great
Q8_01.3 GB319–479 tok/sRuns great
FP162.5 GB289–433 tok/sRuns great

Ran Llama 3.2 1B on a NVIDIA H200 (141GB)? Add your real numbers →