LLM EXPLORER 63,069 MODELS INDEXED

ThinkingCap Qwen3.6 27B Heretic by egibson

By egibson · 55 downloads
HF Repo ↗ Copy URL

ThinkingCap Qwen3.6 27B Heretic is an open-source language model by egibson. Features: 27b LLM, VRAM: 54.7GB, License: apache-2.0, LLM Explorer Score: 0.25.

  Abliterated Base model:bottlecapai/thinkin... Base model:finetune:bottlecapa...   Conversational   Decensored   Efficient-thinking   Endpoints compatible   Heretic   Image-text-to-text   Qwen3 5   Qwen3 6   Region:us   Safetensors   Sharded   Tensorflow   Token-efficient   Uncensored
Model Card on HF 🤗: https://huggingface.co/egibson/ThinkingCap-Qwen3.6-27B-heretic 

ThinkingCap Qwen3.6 27B Heretic Parameters and Internals

LLM NameThinkingCap Qwen3.6 27B Heretic
Repository 🤗https://huggingface.co/egibson/ThinkingCap-Qwen3.6-27B-heretic 
Base Model(s)  bottlecapai/ThinkingCap-Qwen3.6-27B   bottlecapai/ThinkingCap-Qwen3.6-27B
Model Size27b
Required VRAM54.7 GB
Updated2026-08-11
Maintaineregibson
Model Typeqwen3_5
Model Files  2.5 GB: 1-of-12   4.8 GB: 2-of-12   5.0 GB: 3-of-12   4.9 GB: 4-of-12   5.0 GB: 5-of-12   4.9 GB: 6-of-12   4.9 GB: 7-of-12   5.0 GB: 8-of-12   5.0 GB: 9-of-12   4.9 GB: 10-of-12   5.0 GB: 11-of-12   2.8 GB: 12-of-12
Model ArchitectureQwen3_5ForConditionalGeneration
Licenseapache-2.0
Model Max Length262144
Transformers Version5.6.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Errorsreplace

Best Alternatives to ThinkingCap Qwen3.6 27B Heretic

Best Alternatives
Context / RAM
Downloads
Likes
...wopus3.8 27B Flash Mlx OQ4e 1M1024K / 16.9 GB2111
Agens Pilot1024K / 54.7 GB982
Qwen3.8 27B NPU2256K /  GB2524
Clef0K / 54.7 GB42141253
Qwen3.6 27B0K / 55.4 GB67281382197
Qwen3.8 27B0K / 55.6 GB28753
Qwen3.8 27B0K / 55.6 GB272721
Qwen3.8 27B MLX0K / 16 GB141118
Qwen3.8 27B FP80K / 0.4 GB123157416
Qwen3.6 27B NVFP40K / 22 GB1887525419
Note: green Score (e.g. "73.2") means that the model is better than egibson/ThinkingCap-Qwen3.6-27B-heretic.