Can I run this LLM?
Can a NVIDIA H100 SXM (80GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?
Nemotron · openmdw-1.1 · estimated for a 80.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at Q8_0 · 35.0 GB · 248–373 tok/s on a NVIDIA H100 SXM (80GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 18.9 GB | 291–437 tok/s | Runs great |
| Q3_K_M | 19.8 GB | 288–433 tok/s | Runs great |
| Q4_K_M | 25.5 GB | 272–408 tok/s | Runs great |
| Q5_K_M | 27.0 GB | 268–402 tok/s | Runs great |
| Q6_K | 34.3 GB | 250–375 tok/s | Runs great |
| Q8_0 | 35.0 GB | 248–373 tok/s | Runs great |
| FP16 | 65.9 GB | 194–291 tok/s | Tight / slow |
Open the full calculator →Everything a NVIDIA H100 SXM (80GB) 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 H100 SXM (80GB)? Add your real numbers →