Can I run this LLM?
Can a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) run Qwen3.6 35B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 288.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3.6 35B-A3B (MoE) at FP16 · 69.3 GB · 263–395 tok/s on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q3_K_M | 14.9 GB | 333–500 tok/s | Runs great |
| Q4_K_M | 21.0 GB | 324–485 tok/s | Runs great |
| Q5_K_M | 24.7 GB | 318–477 tok/s | Runs great |
| Q6_K | 28.6 GB | 312–469 tok/s | Runs great |
| Q8_0 | 36.8 GB | 301–452 tok/s | Runs great |
| FP16 | 69.3 GB | 263–395 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB) runsQwen3.6 35B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3.6 35B-A3B (MoE) on a NVIDIA GB300 Grace Blackwell (288GB HBM + 480GB)? Add your real numbers →