Qwen 3.6 27B - Claude Fable 5 (Experimental)
GGUFs re-done with MTP built in.
llama.cpp MTP args:
--spec-type draft-mtp --spec-draft-n-max 3
Heres Qwen3.6 slightly over-trained on a very small dataset of fable 5 traces.
Had to use aggressive settings for the style transfer here due to the data contraints. Overall the model seems to be a better planner now and better at 3D modeling in three.js, making small games, and ML engineering.
Either way give it a shot, it really does look, talk, and plan like fable... but like all fine-tunes it comes with it's limitations.
Hopefully we can get some more well rounded data from the rest of the community to a do a much less aggressive tune on a larger dataset.
Reasoning was left untouched
Benchmarks
As always big thanks to @nightmedia for the speedy benchmarks.
arc arc/e boolq
Qwen3.6-27B-Fable-5-Experimental 0.650 0.813 0.909
Qwen3.6-27B 0.637 0.798 0.911
Not really a benchmark but here's a procedurally generated duck that it zero-shotted lol (quant: q3_k_s)
The data for this model was easily extracted, formatted, and masked for training with Teich 
This model was trained 2x faster with Unsloth and Huggingface's TRL library.
