can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 5090 (32GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 32.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q3_K_M · 19.8 GB · 243–365 tok/s on a NVIDIA RTX 5090 (32GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB247–370 tok/sRuns great
Q3_K_M19.8 GB243–365 tok/sRuns great
Q4_K_M25.5 GB222–333 tok/sTight / slow
Q5_K_M27.0 GB217–326 tok/sTight / slow
Q6_K34.3 GB196–294 tok/sWon't fit
Q8_035.0 GB194–291 tok/sWon't fit
FP1665.9 GB137–206 tok/sWon't fit

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a NVIDIA RTX 5090 (32GB)? Add your real numbers →