uncensored ai · Ollama

uncensoredai/diddy

Meet Diddy A Totally Uncesored ,LightWieght Your Coding Assistant.Made By Abhyuday Sinha

tools

369 Pulls 1 Tag Updated 3 weeks ago

uncensoredai/diddy-dev

tools

74 Pulls 1 Tag Updated 3 weeks ago

gurubot/GLM-4.5-Air-Derestricted

uncensored GLM Air

tools thinking

898 Pulls 1 Tag Updated 3 months ago

huihui_ai/homunculus-abliterated

This is an uncensored version of arcee-ai/Homunculus created with abliteration

thinking 12b

2,908 Pulls 5 Tags Updated 9 months ago

huihui_ai/foundation-sec-abliterated

Foundation-Sec-8B-abliterated is an uncensored version fine-tuned based on fdtn-ai/Foundation-Sec-8B. Foundation-Sec-8B is an open-weight, 8-billion-parameter foundational language model designed specifically for cybersecurity applications.

8b

2,456 Pulls 5 Tags Updated 10 months ago

second_constantine/gpt-oss-u

Specialized uncensored quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S. "HERETIC" method results in a model (quantized Q5_1)

thinking 20b

29.3K Pulls 1 Tag Updated 2 months ago

mdq100/Gemma3-Instruct-Abliterated

Gemma3-Instruct-Abliterated model is an instruction-tuned, abliterated, and uncensored AI model built on the Gemma-3 instruction-tuned model from Hugging Face. This Ollama model provides free, honest, and uncensored responses while remaining coherent

vision 12b 27b

18.9K Pulls 2 Tags Updated 6 months ago

StormSplits/shira-1o

Shira-1o is is a new model and smartest uncensored AI with 8B sizes by Storm Splits and team. It is based on Llama 3 that has a variety of instruction, conversational, and coding skills.

738 Pulls 1 Tag Updated 10 months ago

org/deepseek-r1-uncensored

DeepSeek's first-generation of reasoning models with comparable performance to OpenAI-o1, including six dense models distilled from DeepSeek-R1 based on Llama and Qwen.

1,008 Pulls 4 Tags Updated 1 year ago

huihui_ai/seed-coder-abliterate

This is an uncensored version of ByteDance-Seed/Seed-Coder-8B-Instruct created with abliteration

1,506 Pulls 5 Tags Updated 10 months ago

taozhiyuai/llama-3-8b-lexi-uncensored

Lexi is uncensored, which makes the model compliant. You are advised to implement your own alignment layer before exposing the model as a service. It will be highly compliant with any requests, even unethical ones.

19.2K Pulls 9 Tags Updated 1 year ago

slideshow270/llama-3.1-8b-lexi-uncensored-v2

Using Q8 to address issues with Q4.

936 Pulls 1 Tag Updated 1 year ago

vaultbox/qwen3.5-uncensored

www.vaultbox.ai

vision tools thinking 4b 9b 27b 35b

6,825 Pulls 4 Tags Updated 2 weeks ago

aeline/Omega

A small Fine-tuned uncensored model for training 🐁

vision tools

36.3K Pulls 1 Tag Updated 3 months ago

huihui_ai/magistral-abliterated

This is an uncensored version of mistralai/magistral-Small-2506 created with abliteration

thinking 24b

6,206 Pulls 6 Tags Updated 9 months ago

huihui_ai/devstral-abliterated

This is an uncensored version of mistralai/Devstral-Small-2505 created with abliteration

tools 24b

3,519 Pulls 6 Tags Updated 10 months ago

CognitiveComputations/dolphin-mistral-nemo

Dolphin, Uncensored, trained on mistralai/Mistral-Nemo-Base-2407 (12b) 128k context

12b

9,302 Pulls 16 Tags Updated 1 year ago

GandalfBaum/mistralDAN

This is a uncensored mistral 7b model (cas/nous-hermes-2-mistral-7b-dpo) with DAN as its system prompt. I originally intended to use DeepSeek for this, so the model thinks its name is deepseek.

829 Pulls 1 Tag Updated 1 year ago

Malicus7862/thebloke-luna-ai-llama2-uncensored-gguf

Disclaimer: This Model is not my own, but an upload to Ollama from HuggingFace. Quantized by TheBloke, Model creator: Tap Original model: Luna AI Llama2 Uncensored

796 Pulls 1 Tag Updated 1 year ago

nidumai/Nidum-Uncensored-DeepSeek-R1-1776-671B

A variant of the DeepSeek-R1 model, post-trained by Perplexity to deliver unbiased, accurate, and factual information.

302 Pulls 2 Tags Updated 1 year ago