can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Granite 4.2 8B?

Granite · Apache 2.0 · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Granite 4.2 8B at FP16 · 17.6 GB · 129–193 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K3.4 GB260–389 tok/sRuns great
Q3_K_M4.4 GB243–365 tok/sRuns great
Q4_K_M5.4 GB228–342 tok/sRuns great
Q5_K_M6.3 GB216–323 tok/sRuns great
Q6_K7.2 GB204–306 tok/sRuns great
Q8_09.4 GB182–273 tok/sRuns great
FP1617.6 GB129–193 tok/sRuns great

Ran Granite 4.2 8B on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →