Qwen3 8B Heretic (Abliterated) 💬 Community: Join the Abliterlitics Discord for discussion, model releases and support. An abliterated version of Qwen's Qwen3 8B created using Heretic v1.2.0 (git master). This model has reduced refusals while maintaining model quality, making it suitable as an uncensored text encoder for image generation models like Klein 9B. You can see the docker, scripts and configurations used to make these files on Heretic Docker Github. Model Details Base Model: Qwen/Qwen3 8B Abliteration Method: Heretic v1.2.0 (git master, commit 19cdf7e ) Trials: 3000 Trial Selected: Trial 2681 Refusals: 13/100 (vs 100/100 original) KL Divergence: 0.0838 (minimal model damage) Files HuggingFace Format (for transformers, llama.cpp conversion) ComfyUI Format (for Klein 9B text encoder) GGUF Format (for llama.cpp and ComfyUI GGUF) Quant Size Notes F16 16GB Lossless reference Q8 0 8.2GB Excellent quality Q6 K 6.3GB Very good quality Q5 K M 5.5GB Good quality Q5 K S 5.4GB Slightly smaller Q5 Q4 K M 5.0GB Recommended balance Q4 K S 4.8GB Smaller Q4 variant Q3 K M 3.9GB For low VRAM only NVFP4 Notes The NVFP4 (4 bit floating point, E2M1) variants use ComfyUI's native quantization…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy