Qwen3.6-35B-A3B-MTP
2recorded runs
222.9best tok/s
1verified
Fastest GPUs for this model (best tok/s)
- RTX 5090222.9
- RX 7900 XTX x2109.5
| GPU | Model | Quant | Backend | Ctx | tok/s | prompt tok/s | VRAM GB | Source |
|---|---|---|---|---|---|---|---|---|
| RTX 5090 · 32 GB | Qwen3.6-35B-A3B-MTP | Unsloth-Dynamic-IQ4_XS | llama.cpp 10156 | 65536 | 222.9 ✓ | 54.4 | 28.6 | src |
| RX 7900 XTX x2 · 24 GB | Qwen3.6-35B-A3B-MTP | UD-Q4_K_XL | llama.cpp unknown | 2048 | 109.5 … | 175.3 | — | src |