Download a model to run on your own hardware, or run it on Ollama’s cloud.
20+ models
Uncensored Llama 2 model by George Sung and Jarrad Hope.
Uncensored, 8x7b and 8x22b fine-tuned models based on the Mixtral mixture of experts models that excels at coding tasks. Created by Eric Hartford.
The uncensored Dolphin model based on Mistral that excels at coding tasks. Updated to version 2.8.
2.7B uncensored Dolphin model by Eric Hartford, based on the Phi language model by Microsoft Research.
A 7B and 15B uncensored variant of the Dolphin model family that excels at coding, based on StarCoder2.
Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.
Uncensored version of Wizard LM model
Uncensored Llama2 based model with support for a 16K context window.
Meet Diddy A Totally Uncesored ,LightWieght Your Coding Assistant.Made By Abhyuday Sinha
Text + Vision + MTP Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-Q5_NVFP4
https://huggingface.co/HauhauCS/Gemma-4-E4B-Uncensored-HauhauCS-Aggressive
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.
Uncensored DeepSeek-R1-0528-Qwen3-8B via Heretic: 4/100 refusals (from 89), KL 0.041. Reasoning model, MIT.
Uncensored/Abliterated MiMo-V2.6-Distill-Qwen-9B: coding, agent tasks, visual coding, cybersecurity. Thinking+instruct variants.
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
Text + Vision Qwen3.8-27B-FableColdFusion-735882-HereticUncensored-NEOCODERMAX-MTP-NVFP4-Q8-Q3
Uncensored/Abliterated MiniCPM5-2B with only 10/100 refusals. It achieves 2B-class SOTA, remains competitive with 4B models overall.