community-verified · measured pool data
Can the RTX 5060 Ti 16GB ×2 run Qwen3.6-27B-int4-AutoRound?
Yes — community-measured at 69.3 tok/s (2 runs at 4-bit).
Verified single-stream runs on the RTX 5060 Ti 16GB ×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 | 69.3 | 94 | — | 2,048 | vllm |