Self-Hosted AI

State-of-the-art image + text input models from Google, built from the same research and tech used to create the Gemini models

Distilled version of the DeepSeek-R1-0528 model, created by continuing the post-training process on the Qwen3 8B Base model using Chain-of-Thought (CoT) from DeepSeek-R1-0528.

Qwen's latest vision-language model. Includes comprehensive upgrades to visual perception, spatial reasoning, and image understanding.

The first batch of Qwen3 models (Qwen3-2504), a collection of dense and MoE models ranging from 4B to 235B. These are general purpose models that score highly on benchmarks.

Bonsai 27B is PrismML’s family of 1-bit and ternary Qwen3.6 27B models, with vision, reasoning, tool use, and a 262K-token context window.

Ministral 3 series, available in three model sizes: 3B, 8B, and 14B parameters. Provides best of class cost-to-performance ratio.

The latest version of the Qwen3 model family, featuring 4B, 30B, and 235B dense and MoE models, both thinking and non-thinking variants.

State-of-the-art, Mixture-of-Experts local coding model with native support for 256K context length. Available in 30B (3B active) and 480B (35B active) sizes.

Open source coding models by Z.ai, based on a new base model and specializing in coding and tool calling.

Qwen2.5-VL is a performant vision-language model, capable of recognizing common objects and text. Supports context length of 128k tokens in a variety of human languages.

Qwen3 Coder Next is an 80B MoE with 3B active parameters designed for coding agents and local development. Excels at long-horizon reasoning, complex tool usage, and recovery from execution failures.

GLM 4.6V Flash is a 9B vision-language model optimized for local deployment and low-latency applications.

Muse Glimmer is Meta's 30B open model for local agents, combining multimodal understanding, tool use, long-horizon reasoning, and failure recovery.

NVIDIA Nemotron 3 Nano Omni is an open multimodal model with highest efficiency that powers sub-agents to complete tasks faster across vision, audio, and language

Gemma 3n is a generative AI model optimized for use in everyday devices, such as phones, laptops, and tablets.

Phi-4-mini-reasoning is a lightweight open model built upon synthetic data with a focus on high-quality, reasoning dense data.

Second-generation Devstral for agentic coding. Built for tool use to explore codebases, edit multiple files, and power software engineering agents with newly added vision support.

One of the most popular open-source LLMs, Mistral's 7B Instruct model's balance of speed, size, and performance makes it a great general-purpose daily driver.

DeepSeek V4 Flash 0731 is a 284B Mixture-of-Experts model built for coding, tool use, and agentic workflows, with 13B active parameters and a 1M-token context window.

General purpose reasoning and chat model trained from scratch by NVIDIA. Contains 30B total parameters with only 3.5B active at a time for low-latency MoE inference

MistralAI's open-weight reasoning model. 24B dense transformer model supporting up to 128K token context window. The model is capable of long chains of reasoning traces before providing answers.

Granite 4.0 language models are lightweight, state-of-the-art open models that natively support multilingual capabilities, coding tasks, RAG, tool use, and JSON output.

NVIDIA Nemotron 3 Super, a 120B open hybrid MoE model (12B active), supporting up to 1M tokens context window

Laguna S 2.1 is Poolside’s 118B Mixture-of-Experts model for agentic coding and long-horizon tool use, with 8B active parameters and a context window of up to 1M tokens.

LFM2 is a family of hybrid models designed for on-device deployment. LFM2-24B-A2B is the largest model in the family, scaling the architecture to 24 billion parameters while keeping inference efficient.

Mistrall Small is a 'knowledge-dense' 24B multi-modal (image input) local model that supports up to 128 token context length.

The olmOCR 2 model is a Vision Language Model (VLM) from Allen AI.

Devstral is a coding model from Mistral AI. It excels at using tools to explore codebases, editing multiple files and power software engineering agents.

LFM2 is a new generation of hybrid models developed by Liquid AI, specifically designed for edge AI and on-device deployment. It sets a new standard in terms of quality, speed, and memory efficiency.

Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI.