Can I run this LLM?
Can a NVIDIA RTX 6000 Ada (48GB) run Qwen3 Coder Next 80B-A3B (MoE)?
Qwen · Apache 2.0 · estimated for a 48.0 GB machine at 4K context.
Yes — it runs great.
Best fit: Qwen3 Coder Next 80B-A3B (MoE) at Q2_K · 29.2 GB · 206–310 tok/s on a NVIDIA RTX 6000 Ada (48GB).
Every quantization on this machine
| Quant | Size | Speed | Fit |
|---|---|---|---|
| Q2_K | 29.2 GB | 206–310 tok/s | Runs great |
| Q3_K_M | 38.3 GB | 188–282 tok/s | Tight / slow |
| Q4_K_M | 49.3 GB | 169–254 tok/s | Won't fit |
| Q5_K_M | 59.2 GB | 155–233 tok/s | Won't fit |
| Q6_K | 65.8 GB | 147–221 tok/s | Won't fit |
| Q8_0 | 84.8 GB | 128–192 tok/s | Won't fit |
| FP16 | 159.5 GB | 85–128 tok/s | Won't fit |
Open the full calculator →Everything a NVIDIA RTX 6000 Ada (48GB) runsQwen3 Coder Next 80B-A3B (MoE) on other machinesWhat to buy to run it →
Ran Qwen3 Coder Next 80B-A3B (MoE) on a NVIDIA RTX 6000 Ada (48GB)? Add your real numbers →