Ollama
Models Docs Pricing
Sign in Download
Models Download Docs Pricing Sign in
⇅
abliterated · Ollama
Search for models on Ollama.
  • Maternion/spark-x2.5-heretic

    Spark-X2.5-4B abliterated (uncensored) - efficient AI model for chat, writing, coding, reasoning, tools, and agents, 1M-token context, 200+ languages, with refusal behavior removed.

    4b

    263  Pulls 5  Tags Updated  yesterday

  • rafw007/qwen3.8-27b-redteam

    Verified configuration + measured results for abliterated (uncensored) Qwen3.8-27B running as an autonomous redteam/sysadmin agent, served via llama-swap. This card documents OUR tested configuration and results on live tasks

    295  Pulls 1  Tag Updated  3 days ago

  • Maternion/minicpm5-heretic

    Uncensored/Abliterated MiniCPM5-2B with only 10/100 refusals. It achieves 2B-class SOTA, remains competitive with 4B models overall.

    2b

    264  Pulls 5  Tags Updated  3 days ago

  • Ermzzz999/qwen3.6-35b-a3b-abliterated-nvfp4-mtp

    Qwen3.6-35b-a3b-abliterated-nvfp4-mtp-mlx

    vision tools thinking

    64  Pulls 1  Tag Updated  4 days ago

  • ttempvnn/Huihui-gemma-4-31B-it-qat-q4_0-unquantized-abliterated-Q4-K-M

    vision

    26  Pulls 1  Tag Updated  5 days ago

  • orcarouter/Qwen3.8-Flash-Next-Uncensored

    Qwen3.8-Flash-Next tensor-level abliterated— a latest Qwen4-architecture MoE (~177B total / ~6B active) with vision, reasoning, tool-calling, and 262K context. MLX 4/6/8-bit for Apple Silicon. Research use only.

    vision tools thinking

    10.8K  Pulls 4  Tags Updated  3 weeks ago

  • srchmnmichael/Qwen3.8-Uncensored

    Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

    vision tools thinking

    7,193  Pulls 4  Tags Updated  3 weeks ago

  • nandhank/qwen3.5-abliterated-truthful

    Qwen 3.5 Abliterated 9B customized for truthful, direct, and technically rigorous responses. Designed to challenge incorrect assumptions, identify contradictions, avoid hallucinations, and prioritize accuracy over agreement. Strong capabilities in reasoni

    vision tools thinking 9b

    748  Pulls 1  Tag Updated  1 week ago

  • thomboe/dolphin3.0-llama3.1-8b-abliterated

    587  Pulls 1  Tag Updated  3 weeks ago

  • ttempvnn/Huihui-Qwen3.6-35B-A3B-abliterated-Q4-K-M

    vision

    264  Pulls 1  Tag Updated  1 week ago

  • ttempvnn/0bserverx-Qwen3.8-27B-Heretic-Abliterated-Uncensored-multilingual-Q4-K-M

    411  Pulls 1  Tag Updated  4 weeks ago

  • orcarouter/Qwen3.8-27B-Uncensored

    Qwen3.8-27B tensor-level abliterated, vision tower and MTP head untouched. 0% over-refusal on XSTest, 0-6% refusal across the A/B suite, no measurable capability loss. Full mmproj vision, tool calling and thinking, 262K context.

    vision tools thinking

    190K  Pulls 20  Tags Updated  3 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

    1.2M  Pulls 36  Tags Updated  3 months ago

  • ttempvnn/DeepSeek-R1-Distill-Qwen-32B-abliterated-Q4-K-M

    233  Pulls 1  Tag Updated  3 weeks 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

    390K  Pulls 17  Tags Updated  5 months 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

    278.2K  Pulls 1  Tag Updated  4 months ago

  • huihui_ai/Qwen3.8-abliterated

    Qwen3.8 delivers substantial gains across coding, professional work, research, and long-horizon agentic tasks.

    vision tools thinking 27b

    65.6K  Pulls 15  Tags Updated  1 month ago

  • codecraftersllc/ornith-1.5-35b-a3b-abliterated-q2

    129  Pulls 2  Tags Updated  2 weeks ago

  • ninjasatwork/qwen3-omni-abliterated

    vision tools thinking 30b

    116  Pulls 1  Tag Updated  2 weeks ago

  • ttempvnn/Huihui-Qwen3-Next-80B-A3B-Instruct-abliterated-Q4-K-M

    tools thinking

    105  Pulls 1  Tag Updated  3 weeks ago

© 2026 Ollama
Blog Support