Self-Hosted AI

Open-source medical large language model adapted from Llama 2 to the medical domain.

Orca 2 is built by Microsoft research, and are a fine-tuned version of Meta's Llama 2 models. The model is designed to excel particularly in reasoning.

A robust conversational model designed to be used for both chat and instruct use cases.

A language model created by combining two fine-tuned Llama 2 70B models into one.

An extension of Llama 2 that supports a context of up to 128k tokens.

Conversational model based on Llama 2 that performs competitively on various benchmarks.

An extension of Mistral to support context windows of 64K or 128K.

MistralLite is a fine-tuned model based on Mistral with enhanced capabilities of processing long contexts.

Llama 2 based model fine tuned on an Orca-style dataset. Originally called Free Willy.

General use models based on Llama and Llama 2 from Nous Research.

A high-performing code instruct model created by merging two existing code models.

Merge of the Open Orca OpenChat model and the Garage-bAInd Platypus 2 model. Designed for chat and code generation.

Great code generation model based on Llama2.

Fine-tuned Llama 2 model to answer medical questions based on an open source medical dataset.

A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.

Uncensored Llama 2 model by George Sung and Jarrad Hope.

Llama 2 based model fine tuned to improve Chinese dialogue ability.

Wizard Vicuna is a 13B parameter model based on Llama 2 trained by MelodysDreamj.

Wizard Vicuna Uncensored is a 7B, 13B, and 30B parameter model based on Llama 2 uncensored by Eric Hartford.

General use chat model based on Llama and Llama 2 with 2K to 16K context sizes.

Uncensored version of Wizard LM model

A large language model built by the Technology Innovation Institute (TII) for use in summarization, text generation, and chat bots.

StarCoder is a code generation model trained on 80+ programming languages.

A companion assistant trained in philosophy, psychology, and personal relationships. Based on Mistral.

Mistral OpenOrca is a 7 billion parameter model, fine-tuned on top of the Mistral 7B model using the OpenOrca dataset.

Gemma 4 is Google's most capable family of open models, built from Gemini 3 research. Supports vision input and available in multiple sizes for on-device deployment.

Qwen3.5 represents a significant leap forward, integrating breakthroughs in multimodal learning, architectural efficiency, reinforcement learning scale, and global accessibility to empower developers and enterprises with unprecedented capability and efficiency

Qwen3.6 prioritizes stability and real-world utility, offering developers a more intuitive, responsive, and genuinely productive coding experience.

OpenAI's first open source LLM. Comes in 2 sizes: 20B and 120B. Supports configurable reasoning effort (low, medium, high). Trained for tool use. Apache 2.0 licensed.

Qwen3.8-27B is a dense 27B vision-language model for coding, professional work, research, and long-horizon agentic tasks, with configurable reasoning and a native 262K-token context window.