community-verified · measured pool data
Can the RTX 3090 24GB ×2 run Qwen3.6-27B-GGUF?
Yes — community-measured at 37.8 tok/s (3 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 | 37.8 | 1416.1 | 12.2 GB | 65,536 | llama.cpp |
| 8-bit | 23 | 1658.5 | 22.1 GB | 32,768 | llama.cpp |