Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Nemotron 3.5 Lightning 30B-A3B (MoE)?
Nemotron · openmdw-1.1 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Nemotron 3.5 Lightning 30B-A3B (MoE) at FP16 · 65.9 GB · 267–400 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 18.9 GB | 331–496 tok/s | Runs great |
| Q3_K_M | 19.8 GB | 329–494 tok/s | Runs great |
| Q4_K_M | 25.5 GB | 320–480 tok/s | Runs great |
| Q5_K_M | 27.0 GB | 318–477 tok/s | Runs great |
| Q6_K | 34.3 GB | 307–460 tok/s | Runs great |
| Q8_0 | 35.0 GB | 306–459 tok/s | Runs great |
| FP16 | 65.9 GB | 267–400 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) 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 GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →