community-verified · measured pool data
Can the M5 Pro 24GB run Qwen3.6-27B-MTP-GGUF?
Yes — community-measured at 18.2 tok/s (3 runs at 4-bit).
Verified single-stream runs on the M5 Pro 24GB 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 |
|---|---|---|---|---|---|
| 3-bit | 20 | 164 | — | 2,048 | llama.cpp |
| 4-bit | 18.2 | 174.7 | — | 2,048 | llama.cpp |