DeepSeek's first generation reasoning models with comparable performance to OpenAI-o1.
442.6K Pulls 46 Tags Updated 2 months ago
QwQ is an experimental research model focused on advancing AI reasoning capabilities.
57K Pulls 17 Tags Updated 3 weeks ago
Ablitered v3 llama-3.1 8b with uncensored prompt
21.3K Pulls 38 Tags Updated 7 months ago
Qwen2.5-1M is the long-context version of the Qwen2.5 series models, supporting a context length of up to 1M tokens.
18.9K Pulls 11 Tags Updated 2 months ago
This is a phi3 medium model that has had the prompt rejection neurons snipped which is better than fine tuning as it doesn't change how the model acts
5,954 Pulls 1 Tag Updated 10 months ago
Abliterated version of Google's Gemma 2 9B
5,586 Pulls 1 Tag Updated 8 months ago
mlabonne/NeuralDaredevil-8B-abliterated
5,123 Pulls 4 Tags Updated 7 months ago
4,072 Pulls 1 Tag Updated 10 months ago
New state of the art 70B model. Llama 3.3 70B offers similar performance compared to Llama 3.1 405B model.
3,623 Pulls 10 Tags Updated 3 months ago
NeuralDaredevil-8B-abliterated with more quantization
3,406 Pulls 5 Tags Updated 9 months ago
Phi-4 is a 14B parameter, state-of-the-art open model from Microsoft.
3,239 Pulls 5 Tags Updated 2 months ago
The current, most capable model that runs on a single GPU.
3,157 Pulls 14 Tags Updated yesterday
llama3.2:3b abliterated (aka. uncensored)
2,838 Pulls 4 Tags Updated 4 months ago
From huihui-ai/Llama-3.2-11B-Vision-Instruct-abliterated
2,646 Pulls 2 Tags Updated 8 weeks ago
Many quantized GGUF versions of deepseek R1 abliterated (uncensored) with tools support
2,341 Pulls 8 Tags Updated 8 weeks ago
Mistral Small 3 sets a new benchmark in the “small” Large Language Models category below 70B.
2,173 Pulls 10 Tags Updated 8 weeks ago
Abliterated, finetuned and uncensored
1,930 Pulls 1 Tag Updated 10 months ago
Contains fp16 version of the excellent NeuralDaredevil-8B-abliterated
1,924 Pulls 1 Tag Updated 9 months ago
Qwen2.5 7B, but Josiefied and uncensored model
1,696 Pulls 1 Tag Updated 6 months ago
(for 24 GB) Uncensored L3.3 70B, IQ2_XXS and IQ2_XS version
1,632 Pulls 2 Tags Updated 3 months ago