Can I run this LLM?
Can a NVIDIA L40S (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 · 129–193 tok/s on a NVIDIA L40S (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 18.9 GB | 183–274 tok/s | Runs great |
| Q3_K_M | 19.8 GB | 179–268 tok/s | Runs great |
| Q4_K_M | 25.5 GB | 156–234 tok/s | Runs great |
| Q5_K_M | 27.0 GB | 151–227 tok/s | Runs great |
| Q6_K | 34.3 GB | 130–196 tok/s | Runs great |
| Q8_0 | 35.0 GB | 129–193 tok/s | Runs great |
| FP16 | 65.9 GB | 82–123 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA L40S (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 L40S (48GB)? Add your real numbers →