Quantized GGUF of hf.co/OpenYourMind/gemma-4-12B-it-abliterated-uncensored
8,942 Pulls 3 Tags Updated 5 days ago
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.
2,604 Pulls 4 Tags Updated 4 days ago
Quantized GGUF of hf.co/DuoNeural/Gemma4-12B-IT-Abliterated
222 Pulls 3 Tags Updated 5 days ago
25 Pulls 1 Tag Updated 20 hours ago
Cipher-Abliterated is an adaptive conversational AI system designed for flexible interaction, enhanced creative reasoning, and less restrictive conversational behavior while maintaining structured output and technical usability. It is optimized for users
277.6K Pulls 1 Tag Updated 2 weeks ago
Fully decensored Gemma 4 12B (abliterated with Heretic) — 0/100 genuine refusals at KL 0.0284, i.e. near-zero capability loss.
5,614 Pulls 3 Tags Updated 1 week ago
2,232 Pulls 1 Tag Updated 3 weeks ago
2,018 Pulls 1 Tag Updated 3 weeks ago
517 Pulls 1 Tag Updated 2 weeks ago
497 Pulls 1 Tag Updated 3 weeks ago
270 Pulls 1 Tag Updated 1 week ago
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.
280.8K Pulls 36 Tags Updated 10 hours ago
229 Pulls 1 Tag Updated 3 weeks ago
Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.
249K Pulls 58 Tags Updated 2 months ago
Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.
88.3K Pulls 17 Tags Updated 1 month ago
97 Pulls 1 Tag Updated 1 week ago
As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.
60.2K Pulls 5 Tags Updated 4 months ago
Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-fulluncen
9,120 Pulls 2 Tags Updated 1 month ago
Abliterated (decensored) version of google/gemma-4-E4B-it, created using Heretic v1.2.0 with Arbitrary-Rank Ablation (ARA) and row-norm preservation.
10.3K Pulls 5 Tags Updated 2 months ago
12.7K Pulls 1 Tag Updated 3 months ago