community-verified · measured pool data
Can the Radeon AI Pro R9700 32GB ×3 run Qwen3.6-35B-A3B?
Yes — community-measured at 75.2 tok/s (9 runs at 8-bit).
Verified single-stream runs on the Radeon AI Pro R9700 32GB ×3 from the localmaxxing public pool. Every number on this page is measured — nothing here is estimated.
| Quantization | Median tok/s | TTFT (ms) | Peak VRAM | Max context tested | Engines |
|---|---|---|---|---|---|
| 4-bit | 98.9 | 171.4 | 32 GB | 787 | llama.cpp, vllm |
| 8-bit | 75.2 | 308.3 | 44.8 GB | 787 | llama.cpp |