abliterated · Ollama

h4rithd/nullguard

NullGuard is an abliterated research build from gemma4:e4b by h4rithd, made for academic study of local LLM customization, refusal behavior, and safety limits. For research, education, and controlled security testing only.

tools thinking

10 Pulls 1 Tag Updated 6 hours ago

huihui_ai/Qwen3.6-abliterated

Qwen3.6 delivers substantial upgrades in agentic coding and thinking preservation than previous Qwen models.

vision tools thinking 27b 35b

18.3K Pulls 17 Tags Updated 2 weeks ago

nutboy02/Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-uncenfull

Qwen3.6-35B-A3B-Claude-4.7-Opus-abliterated-fulluncen

tools thinking

4,777 Pulls 2 Tags Updated 2 weeks ago

huihui_ai/granite4.1-abliterated

Granite 4.1 models have gone through an improved post-training pipeline, including supervised finetuning and reinforcement learning alignment, resulting in enhanced tool calling, instruction following, and chat capabilities.

tools 3b 8b 30b

1,622 Pulls 12 Tags Updated 1 week ago

charaf/Huihui-Qwen3.6-27B-abliterated-mlx-nvfp4

vision tools thinking

1,286 Pulls 2 Tags Updated 2 days ago

nexusriot/deepseek-r1-abliterated

thinking 8b 14b

1,183 Pulls 2 Tags Updated 4 weeks ago

kwangsuklee/gemma4-e4b-abliterated-Q8

huggingface.co/Jiunsong/supergemma4-e4b-abliterated

tools thinking

723 Pulls 1 Tag Updated 2 weeks ago

charaf/Huihui-Qwen3.6-35B-A3B-abliterated-mlx

vision tools thinking

561 Pulls 2 Tags Updated 2 weeks ago

supergoatscriptguy/mythos-sec

Security-focused local LLM. huihui-4 8B (Gemma-4 abliterated, native thinking) with a hardened system prompt for CTF, bug bounty, pentest methodology, and vulnerability research. Concise, direct, no disclaimers, no refusals. Apache 2.0.

vision tools thinking 8b

408 Pulls 2 Tags Updated 1 week ago

kiwi_kiwi/gemma-4-abliterated-8b

vision tools thinking audio e4b

472 Pulls 1 Tag Updated 2 weeks ago

kiwi_kiwi/Qwen3.6-abliterated

vision tools thinking 27b

296 Pulls 1 Tag Updated 2 weeks ago

huihui_ai/gemma-4-abliterated

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.

vision tools thinking audio e2b e4b 26b 31b 48b

147K Pulls 29 Tags Updated 4 weeks ago