A benchmark of 17 different llama.cpp commits was conducted to determine the fastest version for Qwen3.6 MTP + Vision, totaling 153 successful samples. The commit 57fe1f07c3b6 (b9620), published on June 13, 2026, emerged as the top performer with a score of 95.95 tok/s and a text speed of 89.82 tok/s.

Read original