ThalisAI/Qwen2.5-Coder-32B-Instruct-heretic
33B • Updated • 79
Apostate Models
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
-
-
ThalisAI/Qwen3-VL-32B-Instruct-heretic
33B • Updated • 10 -
ThalisAI/GLM-4.7-Flash-heretic
30B • Updated • 120 -
ThalisAI/Qwen3-VL-8B-Instruct-heretic
8B • Updated • 118 • 1 -
ThalisAI/Qwen2.5-72B-Instruct-heretic
73B • Updated • 88 • 2 -
ThalisAI/DeepSeek-R1-Distill-Llama-70B-heretic
71B • Updated • 195 -
ThalisAI/phi-4-heretic
15B • Updated • 31 -
ThalisAI/Nanbeige4.1-3B-heretic
4B • Updated • 29 -
ThalisAI/Qwen3-32B-heretic
33B • Updated • 20