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
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 18.9 GB | 247–370 tok/s | Runs great |
| Q3_K_M | 19.8 GB | 243–365 tok/s | Runs great |
| Q4_K_M | 25.5 GB | 222–333 tok/s | Tight / slow |
| Q5_K_M | 27.0 GB | 217–326 tok/s | Tight / slow |
| Q6_K | 34.3 GB | 196–294 tok/s | Won't fit |
| Q8_0 | 35.0 GB | 194–291 tok/s | Won't fit |
| FP16 | 65.9 GB | 137–206 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 5090 (32GB) 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 5090 (32GB)? Add your real numbers →