DavidAU/Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-Heretic

🤗 On Hugging Faceimage-text-to-textapache-2.027.4B params55 GBsafetensors✓ Checksum-verifiedupdated 0d ago
Magnet

This model was used as a part of:

https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF

This version exceeds "Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-Heretic" in ALL BENCHMARKS, including scoring OVER 700 in ARC-C for both 8 bit and 4 bit.

(see the benchmarks on the "711" repo.)

Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-Heretic

An Unsloth fine tune on local hardware to specifically raise the model's core intelligence.

Benchmarks:

           arc   arc/e boolq hswag obkqa piqa  wino

Qwen3.6-27B-F451-AND-TRI-Polar-Ultra-Pro-Writer-Uncensored-Heretic [instruct]
mxfp8      0.665,0.830,0.909,...
mxfp4      0.654,0.830,0.905,...

Qwen3.6-27B-Instruct: [base, non heretic]
qx86-hi    0.637,0.798,0.911,0.775,0.442,0.807,0.737

Qwen3.5-27B-Instruct: [base, non heretic]
mxfp8      0.557,0.711,0.868,0.533,0.452,0.706,0.695

Models are tested in "Instruct" mode because this generally works better with the testing harness.

Testing via "thinking" mode also shows the metrics (and changes) but not the true extent.