Qwen3-Coder-30B-A3B-Instruct
2recorded runs
263.0best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 5090263.0
- RTX PRO 6000 Blackwell26.1
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| RTX PRO 6000 Blackwell · 96 GB | Qwen3-Coder-30B-A3B-Instruct | FP8 | vllm 0.26.0 | 32768 | 26.1 ✓ | — | — | src |
| RTX 5090 · 32 GB | Qwen3-Coder-30B-A3B-Instruct | Q6_K | lmstudio unknown | 2048 | 263.0 … | 1217.8 | — | src |