Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Qwen3 Coder 30B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 Coder 30B-A3B (MoE) at Q8_0 · 32.5 GB · 128–192 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 11.3 GB | 206–309 tok/s | Runs great |
| Q3_K_M | 14.7 GB | 188–281 tok/s | Runs great |
| Q4_K_M | 18.6 GB | 171–256 tok/s | Runs great |
| Q5_K_M | 21.7 GB | 159–238 tok/s | Runs great |
| Q6_K | 25.1 GB | 148–222 tok/s | Runs great |
| Q8_0 | 32.5 GB | 128–192 tok/s | Runs great |
| FP16 | 61.1 GB | 85–128 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsQwen3 Coder 30B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3 Coder 30B-A3B (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →