abliterated · Ollama Search

huihui_ai/deepseek-r1-abliterated

DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.

602.6K Pulls 55 Tags Updated 6 months ago

huihui_ai/qwen3-abliterated

Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools thinking 0.6b 1.7b 4b 8b 14b 16b 30b 32b 235b

97.6K Pulls 74 Tags Updated 3 months ago

Drews54/llama3.2-vision-abliterated

From huihui-ai/Llama-3.2-11B-Vision-Instruct-abliterated

vision 11b

70.6K Pulls 2 Tags Updated 10 months ago

huihui_ai/qwq-abliterated

QwQ is an experimental research model focused on advancing AI reasoning capabilities.

tools 32b

66.3K Pulls 17 Tags Updated 9 months ago

huihui_ai/gemma3-abliterated

The current, most capable model that runs on a single GPU.

vision 270m 1b 4b 12b 27b

46.1K Pulls 16 Tags Updated 3 months ago

mannix/llama3.1-8b-abliterated

Ablitered v3 llama-3.1 8b with uncensored prompt

tools

32.4K Pulls 38 Tags Updated 1 year ago

huihui_ai/qwen2.5-1m-abliterated

Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens.

tools 7b 14b

31.7K Pulls 11 Tags Updated 10 months ago

jaahas/qwen3-abliterated

This is the abliterated version of Qwen3, which is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models.

tools 0.6b 1.7b 4b 8b 14b

25.3K Pulls 6 Tags Updated 7 months ago

second_constantine/gpt-oss-u

Specialized uncensored/abliterated quants for new OpenAI 20B MOE - Mixture of Experts Model at 80+ T/S (quantized Q5_1)

thinking 20b

25K Pulls 1 Tag Updated 2 months ago

huihui_ai/llama3.3-abliterated

New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.

tools 70b

23.3K Pulls 10 Tags Updated 11 months ago

huihui_ai/dolphin3-abliterated

Dolphin 3.0 Llama 3.1 8B 🐬 is the next generation of the Dolphin series of instruct-tuned models designed to be the ultimate general purpose local model, enabling coding, math, agentic, function calling, and general use cases.

tools 8b

22.6K Pulls 5 Tags Updated 11 months ago

lstep/neuraldaredevil-8b-abliterated

18.1K Pulls 1 Tag Updated 1 year ago

huihui_ai/qwen3-vl-abliterated

The most powerful vision-language model in the Qwen3 model family to date.

vision tools 2b 4b 8b 30b 32b

17.7K Pulls 54 Tags Updated 3 weeks ago

huihui_ai/gpt-oss-abliterated

OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

tools thinking 20b 120b

15.5K Pulls 16 Tags Updated 2 months ago

huihui_ai/gemma3n-abliterated

This is an uncensored version of google/gemma-3n created with abliteration

14.5K Pulls 2 Tags Updated 4 months ago

tarruda/neuraldaredevil-8b-abliterated

Contains fp16 version of the excellent NeuralDaredevil-8B-abliterated

10K Pulls 1 Tag Updated 1 year ago

huihui_ai/phi4-abliterated

Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.

14b

8,147 Pulls 5 Tags Updated 10 months ago

HammerAI/neuraldaredevil-abliterated

mlabonne/NeuralDaredevil-8B-abliterated

8,102 Pulls 4 Tags Updated 1 year ago

pidrilkin/gemma3_27b_abliterated

vision

6,928 Pulls 1 Tag Updated 7 months ago

redule26/huihui_ai_qwen2.5-vl-7b-abliterated

This is an uncensored version of Qwen/Qwen2.5-VL-7B-Instruct created with abliteration (see remove-refusals-with-transformers to know more about it). Created by https://huggingface.co/huihui-ai

vision

6,892 Pulls 1 Tag Updated 4 months ago