CRACK-abliterated Qwen 3.5 and 3.6 models for MLX on Apple Silicon. Mixed-precision JANGTQ quantization with HarmBench 90%+ and MMLU-neutral profiles.
dealign.ai PRO
dealignai
AI & ML interests
ML Researcher - No fine tuning, no lora, no template bs, pure real ablation. - I have an obsession with making high quality red teaming LLM’s
Recent Activity
updated a collection about 20 hours ago
Qwen 3.5/3.6 CRACK Abliterated updated a collection about 20 hours ago
Qwen 3.5/3.6 CRACK Abliterated updated a model about 21 hours ago
dealignai/Qwen3.6-35B-A3B-JANGTQ2-CRACKOrganizations
These are the empirically proven highest quality uncensored models on MLX.
-
dealignai/MiniMax-M2.7-JANGTQ-CRACK
Text Generation • 15B • Updated • 1.16k • 9 -
dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L
Text Generation • 13B • Updated • 2.66k • 6 -
dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK
Image-Text-to-Text • 3B • Updated • 24.1k • 59 -
dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L
Image-Text-to-Text • 34B • Updated • 1.73k • 4
CRACK-abliterated Qwen 3.5 and 3.6 models for MLX on Apple Silicon. Mixed-precision JANGTQ quantization with HarmBench 90%+ and MMLU-neutral profiles.
These are the empirically proven highest quality uncensored models on MLX.
-
dealignai/MiniMax-M2.7-JANGTQ-CRACK
Text Generation • 15B • Updated • 1.16k • 9 -
dealignai/Nemotron-3-Super-120B-A12B-UNCENSORED-JANG_2L
Text Generation • 13B • Updated • 2.66k • 6 -
dealignai/Gemma-4-26B-A4B-JANG_2L-CRACK
Image-Text-to-Text • 3B • Updated • 24.1k • 59 -
dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L
Image-Text-to-Text • 34B • Updated • 1.73k • 4
models 90
dealignai/Qwen3.6-35B-A3B-JANGTQ2-CRACK
Image-Text-to-Text • 3B • Updated • 354 • 2
dealignai/Qwen3.6-35B-A3B-JANGTQ4-CRACK
Image-Text-to-Text • 5B • Updated • 155
dealignai/MiniMax-M2.7-JANGTQ-CRACK
Text Generation • 15B • Updated • 1.16k • 9
dealignai/Mistral-Small-4-119B-JANG_2L-CRACK
Image-Text-to-Text • 12B • Updated • 744 • 2
dealignai/Mistral-Small-4-119B-JANG_4M-CRACK
Image-Text-to-Text • 19B • Updated • 749 • 4
dealignai/Nemotron-Cascade-2-30B-A3B-UNCENSORED-JANG_2L
Text Generation • 5B • Updated • 1.01k • 2
dealignai/Nemotron-Cascade-2-30B-A3B-JANG_2L-CRACK
Text Generation • 3B • Updated • 713 • 4
dealignai/Qwen3.5-VL-397B-A17B-JANG_2L-CRACK
Image-Text-to-Text • 54B • Updated • 730 • 1
dealignai/Qwen3.5-VL-397B-A17B-UNCENSORED-JANG_1L
Image-Text-to-Text • 34B • Updated • 1.73k • 4
dealignai/Qwen3.5-VL-9B-JANG_4S-CRACK
Image-Text-to-Text • 2B • Updated • 1.9k • 4
datasets 0
None public yet