Qwen 3.6 27B dense is much better than the 35B MoE model for coding, not sure if you've tried that yet.
27b is slow as molasses vs 35b on local stuff I have (m5 max). Mtp doesn’t make any difference either.
yes, I have, I use both. 27B slower in tok/s due to density, obviously, 35B-A3B for speed on simpler tasks.
27b is slow as molasses vs 35b on local stuff I have (m5 max). Mtp doesn’t make any difference either.