Can I run this LLM?
Can a NVIDIA RTX Pro 6000 Blackwell (96GB) run Qwen3 30B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 96.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 30B-A3B (MoE) at FP16 · 61.1 GB · 132–198 tok/s on a NVIDIA RTX Pro 6000 Blackwell (96GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 9.9 GB | 266–398 tok/s | Runs great |
| Q3_K_M | 13.2 GB | 250–374 tok/s | Runs great |
| Q4_K_M | 18.5 GB | 227–341 tok/s | Runs great |
| Q5_K_M | 21.8 GB | 215–323 tok/s | Runs great |
| Q6_K | 25.2 GB | 204–306 tok/s | Runs great |
| Q8_0 | 32.4 GB | 184–276 tok/s | Runs great |
| FP16 | 61.1 GB | 132–198 tok/s | Runs great |
Open the full calculator →Everything a NVIDIA RTX Pro 6000 Blackwell (96GB) runsQwen3 30B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3 30B-A3B (MoE) on a NVIDIA RTX Pro 6000 Blackwell (96GB)? Add your real numbers →