Models

igorls/gemma-4-12B-it-heretic-GGUF

Fully decensored Gemma 4 12B (abliterated with Heretic) — 0/100 genuine refusals at KL 0.0284, i.e. near-zero capability loss.

maxwellb/gemma4-12b-it-oym

Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored

igorls/gemma-4-12B-it-qat-q4_0-unquantized-heretic

Decensored (abliterated) Gemma 4 12B — refusals removed with Heretic while keeping the base model's intelligence (KL 0.0154, 0 true refusals). For uncensored assistant and 18+ companion/roleplay use.

HammerAI/gemma-4-12b-heretic

igorls/gemma-4-12B-it-heretic-v1

scorpion7slayer/gemma-4-12b-it-claude-4.6-4.8-opus

https://huggingface.co/yuxinlu1/gemma-4-12B-it-Claude-4.6-4.8-Opus-GGUF

baytout3/gemma-4-12B-it-uncensored-opus4.7-cot-GGUF

ttempvnn/Huihui-gemma-4-12B-it-qat-q4_0-unquantized-abliterated-Q4-K-M

MobiusDevelopment/gemma-4-12B-it-qat-q4_0-gguf

Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

fynnhaupt2/unsloth-gemma-4-12b-it-qat-gguf

https://huggingface.co/unsloth/gemma-4-12B-it-qat-GGUF

ttempvnn/Igorls-gemma-4-12B-it-heretic-GGUF-Q8-0

📝 A copy by author Igorls. I tested it, the quality is excellent! 👍👍👍

baytout3/gemma-4-12B-it-qat-q4_0-gguf

thox-ai/thoxnova-12b-agent

THOX.ai tool-calling agent. Gemma-4-12B-it QLoRA fine-tune, Q4_K_M, with tools and thinking.