Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
abliterated · Ollama
Search for models on Ollama.
  • 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.

    150  Pulls 1  Tag Updated  4 days ago

  • dzgg/qwen3.5-abliterated

    vision tools thinking 4b

    94  Pulls 1  Tag Updated  3 days ago

  • dzgg/gemma-4-abliterated

    vision tools thinking

    77  Pulls 1  Tag Updated  3 days ago

  • kokololo/whoamisec-ai

    abliterated

    tools

    23  Pulls 1  Tag Updated  5 days ago

  • dzgg/qwen3-abliterated

    tools thinking

    17  Pulls 1  Tag Updated  3 days ago

  • maxwellb/gemma4-12b-it-oym

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

    vision tools thinking

    11K  Pulls 3  Tags Updated  2 weeks ago

  • 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.

    tools thinking

    6,903  Pulls 3  Tags Updated  2 weeks ago

  • 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.

    tools thinking

    4,345  Pulls 4  Tags Updated  2 weeks ago

  • kiwi_kiwi/gemma-4-12B-abliterated

    tools thinking

    478  Pulls 1  Tag Updated  1 week ago

  • aratan/qwen3.5-9b-abliterated-flash

    vision tools thinking

    421  Pulls 1  Tag Updated  1 week ago

  • kaelri/qwen3.5-abliterated-nonthinking

    vision tools 2b

    676  Pulls 1  Tag Updated  3 weeks ago

  • levy52/Qwen3.6-abliterated

    vision tools thinking 35b

    281  Pulls 1  Tag Updated  1 week ago

  • vatistasdim/Cipher-Abliterated

    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

    tools

    277.8K  Pulls 1  Tag Updated  4 weeks ago

  • maxwellb/gemma4-12b-it-dn

    Quantized GGUF of hf.co/DuoNeural/Gemma4-12B-IT-Abliterated

    vision tools thinking

    367  Pulls 3  Tags 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 12b 26b 31b 48b

    431.2K  Pulls 36  Tags Updated  1 week ago

  • oroboroslabs/qwen3.5-abliterated-47-4

    vision tools thinking

    328  Pulls 1  Tag Updated  3 weeks ago

  • alexanderschneider/gemma-4-abliterated

    vision tools thinking audio

    165  Pulls 1  Tag Updated  1 week ago

  • huihui_ai/qwen3.5-abliterated

    Qwen 3.5 is a family of open-source multimodal models that delivers exceptional utility and performance.

    vision tools thinking 0.8b 2b 4b 9b 27b 35b 122b

    308.9K  Pulls 58  Tags Updated  2 months 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

    144K  Pulls 17  Tags Updated  2 months ago

  • huihui_ai/glm-4.7-flash-abliterated

    As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

    tools thinking

    110.4K  Pulls 5  Tags Updated  4 months ago

© 2026 Ollama
Blog Contact