can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Llama 3.2 3B?

Llama · Llama 3.2 Community · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Llama 3.2 3B at FP16 · 6.4 GB · 216–324 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q4_K_M1.9 GB295–442 tok/sRuns great
Q5_K_M2.3 GB287–430 tok/sRuns great
Q6_K2.6 GB279–418 tok/sRuns great
Q8_03.4 GB263–395 tok/sRuns great
FP166.4 GB216–324 tok/sRuns great

Ran Llama 3.2 3B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →