abliterated · Ollama

bergencvv/glm5.2-abliterated

44 Pulls 1 Tag Updated 5 days ago

bergencvv/deepseek-v4-flash-abliterated

5 Pulls 1 Tag Updated 19 hours ago

bergencvv/superhy3-abliterated

3 Pulls 1 Tag Updated 19 hours ago

richardyoung/qwythos-9b-abliterated

Abliterated build of Qwythos-9B-Claude-Mythos, a Claude-style creative & reasoning model (Qwen3.5-9B base) with refusals further reduced via the Heretic library.

10.7K Pulls 6 Tags Updated 3 weeks ago

rafw007/Qwen3.6-35B-A3B-mlx-claude-coder-abliterated

A custom model built on Qwen3.6-35B-A3B (abliterated), tuned to act as an autonomous coding and administration agent. It speaks the Anthropic-compatible API, so it drives Claude Code fully locally — your code never leaves your machine.

vision tools thinking

2,609 Pulls 1 Tag Updated 2 weeks ago

richardyoung/qwen3.6-27b-abliterated

Abliterated (uncensored) version of **Qwen/Qwen3.6-27B**, refusal behavior reduced via targeted weight modification with the Heretic library, while preserving coherence.

2,770 Pulls 6 Tags Updated 3 weeks ago

chatgpt1/qwythos-9b-claude-mythos-5-1m-abliterated

Qwythos-9B-Claude-Mythos-5-1M-abliterated

919 Pulls 1 Tag Updated 1 week ago

richardyoung/qwen2.5-14b-instruct-abliterated

Uncensored, abliterated build of [Qwen/Qwen2.5-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-14B-Instruct), Alibaba's capable 14B instruct model

927 Pulls 2 Tags Updated 3 weeks ago

richardyoung/qwable-9b-abliterated

Abliterated build of Qwable-9B-Claude-Fable, a Claude-style creative and reasoning model (Qwen3.5-9B base) with refusals reduced via the Heretic library.

826 Pulls 6 Tags Updated 3 weeks ago

richardyoung/llama-3.2-3b-instruct-abliterated

Uncensored, abliterated build of [meta-llama/Llama-3.2-3B-Instruct](https://huggingface.co/meta-llama/Llama-3.2-3B-Instruct), Meta's compact instruct model with safety refusals surgically removed via [Heretic](https://github.com/p-e-w/heretic).

815 Pulls 2 Tags Updated 3 weeks ago

richardyoung/qwen2.5-coder-14b-instruct-abliterated

Uncensored, abliterated build of [Qwen/Qwen2.5-Coder-14B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-14B-Instruct), Alibaba's flagship 14B coding model

743 Pulls 2 Tags Updated 3 weeks ago

richardyoung/gemma-4-12b-coder-abliterated

a Gemma-4 12B coding model with refusals dramatically reduced via the Heretic library.

tools thinking

641 Pulls 6 Tags Updated 3 weeks ago

lileilei999/qwen3.5-9b-abliterated-vision

vision

348 Pulls 1 Tag Updated 1 week ago

aratan/qwen3.6-claude-coder-35b-A3b-mlx-Q4KM-abliterated

Muy rapido en RTX 4060 21 a 27 T/S

vision tools thinking

411 Pulls 1 Tag Updated 1 week ago

richardyoung/qwen2.5-3b-instruct-abliterated

Uncensored, abliterated build of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct), Alibaba's compact instruct model

514 Pulls 2 Tags Updated 3 weeks ago

lileilei999/gemma-4-abliterated

vision tools thinking 12b

270 Pulls 1 Tag Updated 1 week ago

richardyoung/qwen3-4b-instruct-2507-abliterated

Uncensored, abliterated build of [Qwen/Qwen3-4B-Instruct-2507](https://huggingface.co/Qwen/Qwen3-4B-Instruct-2507), Alibaba's 4B non-thinking instruct model

459 Pulls 2 Tags Updated 3 weeks ago

kaineone/qwen3.5-4b-abliterated

Abliterated (refusal-direction removed, Arditi et al. 2024) variant of `Qwen/Qwen3.5-4B`. **Not** fine-tuned — no preference/instruction data added; only the refusal direction is orthogonalized out.

516 Pulls 1 Tag Updated 3 weeks ago

richardyoung/qwen3.6-27b-code-abliterated

Code-safety abliterated build of Qwen/Qwen3.6-27B, refusals on malicious-code requests reduced via a *code-specific* refusal-direction ablation, while preserving coherence.

415 Pulls 5 Tags Updated 3 weeks ago

HammerAI/qwen3.5-abliterated

huihui_ai/qwen3.5-abliterated

vision tools thinking

291 Pulls 2 Tags Updated 2 weeks ago