can-i-run-this-llm

Can I run this LLM?

Can a NVIDIA RTX 3090 (24GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?

Nemotron · openmdw-1.1 · estimated for a 24.0 GB machine at 4K context.

Yes, but it's tight.

Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q3_K_M · 19.8 GB · 186–279 tok/s on a NVIDIA RTX 3090 (24GB).

Every quantization on this machine

QuantSizeSpeedFit
Q2_K18.9 GB190–285 tok/sTight / slow
Q3_K_M19.8 GB186–279 tok/sTight / slow
Q4_K_M25.5 GB163–245 tok/sWon't fit
Q5_K_M27.0 GB158–237 tok/sWon't fit
Q6_K34.3 GB137–206 tok/sWon't fit
Q8_035.0 GB135–203 tok/sWon't fit
FP1665.9 GB87–131 tok/sWon't fit
Open the full calculator →Everything a NVIDIA RTX 3090 (24GB) 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 3090 (24GB)? Add your real numbers →