Qwen 3.6 27B Claude Fable 5 (Experimental) Update · 6/22/2026 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. 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.
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy