can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 6000 Ada (48GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 48.0 GB machine at 4K context.

Yes — it runs great.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q8_0 · 35.0 GB · 138–206 tok/s on a NVIDIA RTX 6000 Ada (48GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB192–289 tok/sRuns great
Q3_K_M19.8 GB188–282 tok/sRuns great
Q4_K_M25.5 GB166–248 tok/sRuns great
Q5_K_M27.0 GB160–241 tok/sRuns great
Q6_K34.3 GB139–209 tok/sRuns great
Q8_035.0 GB138–206 tok/sRuns great
FP1665.9 GB89–134 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsNemotron 3.5 Lightning 30B-A3B (MoE) on other machinesWhat to buy to run it →

Ran Nemotron 3.5 Lightning 30B-A3B (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →