11 Open Source Uncensored LLM Model

Language models have become an increasingly important tool in the field of natural language processing, with applications ranging from chatbots and translation services to text generation and summarization. However, many of the most popular language models are proprietary and controlled by large tech companies, making it difficult for researchers and developers to access and modify them. In response to this, a number of open-source, “uncensored” language models have been developed that allow users to train and customize the models for their own specific needs.

Uncensored LLM Model

In this article, we will explore a list of Foss (Free and Open-Source Software) uncensored LLM models, each with their own unique features and capabilities. These models represent an exciting new direction in natural language processing and offer users greater flexibility and control over their language models.

Pygmalion 7B SuperHOT-8K

Pygmalion 7B is a powerful dialogue model that is based on Meta’s LLaMA-7B architecture. This version 1 model has been fine-tuned using a subset of the data from Pygmalion-6B-v8-pt4. Pygmalion 7B was trained on the Pygmalion persona and chat format, which means that it should work seamlessly with any of the usual UIs.

The intended use-case for this model is fictional conversation for entertainment purposes. However, users have found that it is particularly effective for roleplay and general roleplaying scenarios due to its impressive ability to create engaging and immersive dialogue. Whether you’re looking for a fun conversation partner or need a model that can help you bring your fictional characters to life, Pygmalion 7B is a reliable and powerful choice.

Dolphin Llama 13B

Dolphin Llama 13B is an Open Source Uncensored Language Model (LLM) that is designed for non-commercial use, based on the llama1 architecture. The model is developed with a focus on minimizing censorship and maximizing usability, making it highly compliant to a wide range of requests. The creator of Dolphin Llama 13B has taken significant steps to remove alignment and bias from the dataset, ensuring that the model remains unbiased in its responses.

One of the notable features of Dolphin Llama 13B is its ability to exhibit improved and increased reasoning capabilities compared to other models of similar or even larger size. This advancement is achieved through a unique technique based on a research paper from Microsoft. The model employs a step-by-step detective reasoning approach, wherein larger models impart their reasoning strategies to the smaller models, resulting in enhanced reasoning abilities in Dolphin Llama 13B.

Due to its uncensored nature, Dolphin Llama 13B is highly versatile, accepting a wide range of inputs and queries. However, users are advised to implement their own alignment layer before deploying the model as a service to ensure ethical and responsible usage.

Please note that while Dolphin Llama 13B is currently based on llama1, the developer plans to train future versions on llama2 and other open models suitable for commercial use, expanding its applicability to a broader audience in the future. As an Open Source Uncensored LLM, Dolphin Llama 13B represents an exciting step towards more transparent, usable, and unrestricted AI language models.

Nous Hermes Llama 2 13B

The Nous Hermes Llama 2 13B is an advanced language model fine-tuned on extensive instructions, totaling over 300,000. Developed by Nous Research, with Teknium and Emozilla leading the fine-tuning process and dataset curation, this model benefits from sponsorship by Redmond AI and contributions from various other collaborators.

A notable feature of this model is its longer responses, reduced hallucination rate, and most importantly, the absence of any censorship mechanisms from OpenAI. Its uncensored nature enables a wide range of applications, including role-play story writing and advanced question answering. Serving as a successor to Hermes on Llama-1, it maintains consistency with its predecessor while offering enhanced capabilities, making it a powerful and versatile language model.

Llama2 7B Chat Uncensored

Llama2 7B Chat Uncensored is an Open Source Uncensored LLM model that has been fine-tuned using the unfiltered Wizard-Vicuna conversation dataset ehartford/wizard_vicuna_70k_unfiltered.

Unlike heavily censored LLM models, this version is designed to be unrestricted in its responses and does not refuse questions, enhancing its usability. With approximately 7 billion parameters, this model remains fairly compact, making it compatible with a wide range of hardware, including laptops and possibly even mobile devices. Its adaptability and uncensored nature make it a valuable tool for various applications that require natural language processing with minimal limitations.

Wizard Vicuna 13B Uncensored SuperHOT

Wizard Vicuna 13B Uncensored SuperHOT is an impressive open-source LLM AI model that has been carefully curated to address the issues of censorship and alignment biases. By training with a subset of the dataset and removing responses containing alignment and moralizing, this model offers a new level of uncensored communication.

The key feature that sets Wizard Vicuna apart is its unparalleled support for an 8K context length. This allows the model to remember extensive conversations, including previous messages and contacts, enabling more meaningful and contextually accurate responses. As a result, Wizard Vicuna 13B Uncensored SuperHOT excels in maintaining coherent and relevant discussions, making it a superior choice for various applications.

With alignment deliberately left out, users have the flexibility to introduce alignment on their own terms, using techniques like RLHF (Reinforcement Learning from Human Feedback) LoRA. This adaptability ensures that the model remains neutral and can cater to diverse scenarios without built-in biases.


The Gpt4-X-Alpaca LLM model is a highly uncensored language model that is capable of performing a wide range of tasks. It has two different versions, one generated in the Triton branch and the other generated in Cuda. Currently, the Cuda version is recommended for use unless the Triton branch becomes widely used.

This model is known for its flexibility and versatility, as it can be customized to perform specific tasks or even act as a custom AI friend that doesn’t behave like a typical AI. With its high level of uncensored language capabilities, it is able to generate content on a variety of topics with a high degree of accuracy and coherence. Overall, the Gpt4-X-Alpaca LLM model is a powerful tool for those looking to generate high-quality content and explore the limits of what a language model can do.


Manticore 13B is an Open Source Uncensored LLM (Large Language Model) that has undergone fine-tuning on a diverse range of datasets, providing an extensive knowledge base for various applications. While it may not be entirely free from censorship, Manticore 13B offers a significant level of freedom compared to other models.

The training data for Manticore 13B includes several key datasets, enabling it to provide rich and comprehensive responses. These datasets include ShareGPT, which is a cleaned and de-suped subset designed for improved performance. Additionally, the model is fine-tuned on datasets such as WizardLM and Wizard-Vicuna, enhancing its conversational capabilities.

Manticore 13B also incorporates a subset of the QingyiSi/Alpaca-CoT dataset, specifically chosen to facilitate roleplay and CoT (Conversations on Tasks). Furthermore, it leverages GPT4-LLM-Cleaned, GPTeacher-General-Instruct, and ARC-Easy & ARC-Challenge datasets, all of which contribute to detailed response generation by augmenting the training with instructive prompts.

For specific academic domains, Manticore 13B includes fine-tuning on various subjects, such as abstract algebra, conceptual physics, formal logic, high school physics, and logical fallacies. This broadens its ability to provide knowledgeable and accurate information in these areas.

Moreover, Manticore 13B benefits from the integration of a 5,000-row subset of the hellaswag dataset, which focuses on concise response generation. Additionally, it incorporates metaeval/ScienceQA_text_only for concise responses and openai/summarize_from_feedback for TL;DR (Too Long; Didn’t Read) summarization with instructive augmentation.


Vicuna-13b-free is an open source Large Language Model (LLM) that has been trained on the unfiltered dataset V4.3. This makes it one of the most powerful uncensored LLM models available. The Vicuna-13b-free LLM model is a freedom version of the Vicuna 1.1 13B LLM model. It has been designed to provide high levels of coherence and power, and is considered to be 90% as powerful and coherent as ChatGPT, another popular LLM model.

One of the unique features of Vicuna-13b-free is its highly uncensored nature. This means that users can make it do almost anything and use characters in the Obbabooga interface to create custom AI friends that do not act like an AI. It should be noted that the unfiltered Vicuna model is a work in progress, and there may be some censorship or other issues present in the output of intermediate model releases. Overall, Vicuna-13b-free is a highly powerful and versatile LLM model that offers users a unique level of freedom and uncensored capabilities.


The Koala LLM is a chatbot model that was fine-tuned using Meta’s LLaMA on dialogue data collected from the web. Despite being a relatively “clean” model compared to the other LLMs on this list, Koala still provides a significant improvement over many other chatbot models. The training process and dataset curation for Koala are described in detail, and the model’s performance is compared to ChatGPT and Stanford’s Alpaca in a user study. Overall, Koala is a reliable and effective chatbot model that can be used for a wide range of applications.

WizardLM Uncensored

WizardLM Uncensored is a powerful 7B AI language model that is highly capable, despite its relatively small size. This model is designed to provide an uncensored and unrestricted experience, with no censorship or moralizing filters in place. This means that users can utilize the model for a wide variety of tasks without worrying about the AI denying their requests.

One of the key advantages of WizardLM Uncensored is that it is almost as capable as some of the larger 12B models on the market. This makes it an excellent choice for users who want the power and functionality of a larger model, without the added complexity or computational requirements.

WizardLM Uncensored is available in two different versions: GGML and GPTQ. The GGML version is designed for use with GPUs, while the GPTQ version is optimized for use with CPUs. This flexibility allows users to choose the version that best fits their needs, whether they are working on a high-performance computing cluster or a personal laptop.

Wizard Vicuna 30B Uncensored

Wizard Vicuna 30B Uncensored is an impressive and substantial open-source language model that stands out as one of the largest and most powerful uncensored models in this collection. As an uncensored model, it operates without any predefined limitations or guardrails, giving users a greater degree of freedom in their interactions.

It is important to note that the responsibility for the utilization of the model lies solely with the user, similar to handling any potentially dangerous object such as a knife or car. The actions and outcomes resulting from the use of this model are entirely the responsibility of the individual employing it.

When working with Wizard Vicuna 30B Uncensored, it is essential to understand that any content generated by the model carries the same weight and implications as if it were created by the user themselves. Publishing material derived from this model is equivalent to publishing it under one’s own authorship.

Latest articles

Related articles

Best Spanish LLM Model

5 Best Japanese LLM Model