community-verified · measured pool data
Can the Multi-GPU 28GB ×2 run Qwen3.6-35B-A3B?
Yes — community-measured at 85.6 tok/s (4 runs at 4-bit).
Verified single-stream runs on the Multi-GPU 28GB ×2 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 | 85.6 | 81.1 | — | 4,096 | llama.cpp |