Uncensored LLMs converted using an automated, iterative heretic pipeline.
Qwen2.5-Coder-32B model is the best, followed by Qwen3 and GLM-4.7-Flash
Thalis AI
ThalisAI
AI & ML interests
None yet
Recent Activity
updated
a model
about 15 hours ago
ThalisAI/Qwen3-32B-heretic
updated
a collection
about 15 hours ago
Apostate Models
updated
a model
1 day ago
ThalisAI/Nanbeige4.1-3B-heretic
Organizations
None yet
models
10
ThalisAI/Qwen3-32B-heretic
33B
•
Updated
•
462
ThalisAI/Nanbeige4.1-3B-heretic
4B
•
Updated
•
507
ThalisAI/Qwen3-VL-32B-Instruct-heretic
33B
•
Updated
•
121
ThalisAI/Qwen3-VL-8B-Instruct-heretic
8B
•
Updated
•
96
ThalisAI/DeepSeek-R1-Distill-Llama-70B-heretic
71B
•
Updated
•
166
ThalisAI/phi-4-heretic
15B
•
Updated
•
95
ThalisAI/Qwen2.5-Coder-32B-Instruct-heretic
33B
•
Updated
•
99
ThalisAI/Qwen2.5-72B-Instruct-heretic
73B
•
Updated
•
167
ThalisAI/GLM-4.7-Flash-heretic
30B
•
Updated
•
155
ThalisAI/graveyard_ghoulz
Text-to-Image
•
Updated
datasets
0
None public yet