can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 144.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at FP16 · 65.9 GB · 228–342 tok/s on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB312–467 tok/sRuns great
Q3_K_M19.8 GB309–464 tok/sRuns great
Q4_K_M25.5 GB296–444 tok/sRuns great
Q5_K_M27.0 GB293–440 tok/sRuns great
Q6_K34.3 GB278–417 tok/sRuns great
Q8_035.0 GB277–415 tok/sRuns great
FP1665.9 GB228–342 tok/sRuns great

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a NVIDIA GH200 Grace Hopper (144GB HBM + 480GB)? Add your real numbers →