community-verified · measured pool data
Can the RTX 4070 12GB run Qwen3.6-27B-GGUF?
Yes — community-measured at 21.1 tok/s (2 runs at 2-bit).
Verified single-stream runs on the RTX 4070 12GB 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 |
|---|---|---|---|---|---|
| 2-bit | 21.1 | 1390.9 | 11.9 GB | 98,304 | llama.cpp |