Downloads · 30 days
21
5% of all-time downloads
gorbatjovy/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic
Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic is a machine learning model from gorbatjovy. Use it for the machine learning task on the model card, and read the license before you ship it in a product.
Heretic 1.4 quant of https://huggingface.co/nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451
Downloads · 30 days
21
5% of all-time downloads
All-time downloads
429
Public
Parameters
27.4B
55.6 GB on disk
Likes
10
Public
Click a slice to open those files.
.safetensors55.6 GB · 100%
From the Hugging Face model README
Heretic 1.4 quant of https://huggingface.co/nightmedia/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451
Refusals: 4/100, KL divergence: 0.0074
UPDATE: 2026-07-27 - Fixed the MTP layers, thanks to @DavidAU for the script https://huggingface.co/DavidAU/Qwen3.6-27B-Fable-Fusion-711-Uncensored-Heretic-NM-DAU-NEO-MAX-MTP-GGUF/resolve/main/__merge-mtpKEYS-with-finetune.py
GGUF Available here: https://huggingface.co/gorbatjovy/Qwen3.6-27B-Architect-Polaris2-Fable-B-F451-heretic-GGUF