can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA A100 (80GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 80.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q8_0 · 35.0 GB · 206–308 tok/s on a NVIDIA A100 (80GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB257–386 tok/sRuns great
Q3_K_M19.8 GB254–380 tok/sRuns great
Q4_K_M25.5 GB233–350 tok/sRuns great
Q5_K_M27.0 GB229–343 tok/sRuns great
Q6_K34.3 GB207–311 tok/sRuns great
Q8_035.0 GB206–308 tok/sRuns great
FP1665.9 GB149–223 tok/sTight / slow

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a NVIDIA A100 (80GB)? Add your real numbers →