community-verified · measured pool data
Can the RTX 5090 32GB run Qwen3.6-27B-MTP-GGUF?
Yes — community-measured at 64 tok/s (3 runs at 5-bit).
Verified single-stream runs on the RTX 5090 32GB 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 |
|---|---|---|---|---|---|
| 5-bit | 64 | 140.8 | 26.4 GB | 131,072 | llama.cpp |