community-verified · measured pool data
Can the RTX 3090 24GB ×2 run Qwen3.6-27B?
Yes — community-measured at 41.2 tok/s (4 runs at 4-bit).
Verified single-stream runs on the RTX 3090 24GB ×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 | 41.2 | 345.9 | 24.3 GB | 131,712 | llama.cpp, vllm |