Ollama
Ollama lets you download and run open AI models on your own computer, or use them in the cloud, with a local API that connects to apps and coding agents.
About this tool
Ollama is one of the simplest ways to run open large language models on your own computer. A single command downloads a model such as Qwen, Gemma, DeepSeek or gpt-oss and starts it locally, and a REST API lets other applications use it. It runs on desktop operating systems and as an official Docker image.
Ollama now also offers cloud models for workloads too heavy for a laptop, billed with usage credits per million tokens and cheaper off-peak hours. It connects to coding agents and tools such as Claude Code, Codex, Copilot CLI and OpenCode, and a large ecosystem of community interfaces builds on it. Ollama states that prompts are not stored or used for training.
What you can do
Local model runtime
Download and run open models with one command, keeping prompts and data on your own machine.
Model library
A library of popular open models in different sizes lets you trade quality for speed depending on your hardware.
REST API and integrations
Applications and coding agents can call Ollama’s local API, and official integrations cover several popular agent tools.
Cloud models and team plan
Run larger models in Ollama’s cloud with pay-as-you-go credits, and manage shared usage, budgets and model access for teams.
Who is it for?
- A developer runs a coding model offline on a laptop during travel.
- A privacy-conscious team tests open models without sending data to a third-party API.
- A hobbyist connects a local model to a chat interface such as Open WebUI.
Before you choose
Local performance depends heavily on your GPU and memory; large models may be slow or impossible to run on modest hardware.
Each open model has its own licence, so check the terms before using one in a commercial product.
Frequently asked questions
Is Ollama free?
Running open models locally with Ollama is free. Cloud models use pay-as-you-go credits, and a Team plan adds shared billing.
Which models can Ollama run?
Ollama supports many open models, including Qwen, Gemma, DeepSeek, gpt-oss, Kimi, GLM and MiniMax, listed in its library.
Can Ollama work with coding agents?
Yes, Ollama integrates with tools such as Claude Code, Codex, Copilot CLI and OpenCode so they can use local or cloud models.
Check the official website for current features, pricing, and terms.
Similar tools
LM Studio
CodingLM Studio is a desktop app for discovering and running open AI models locally, with an agent called Bionic, developer APIs and local voice transcription.
Jan
CodingJan is a free, open-source desktop app for chatting with AI models that run offline on your computer, with optional connections to cloud models.
DeepSeek
CodingDeepSeek develops large language models, including open-weight reasoning models, offered through a chat app and an OpenAI-compatible developer API.
Anthropic API
CodingThe Anthropic API, part of the Claude Platform, lets developers build applications and agents on Claude models with tools for code execution, computer use and structured output.
Replicate
CodingReplicate runs open-source and proprietary AI models through a cloud API, and lets developers fine-tune models or deploy their own without managing GPUs.
Devin Desktop (formerly Windsurf)
CodingDevin Desktop is the new name for Windsurf: Cognition’s AI code editor, now organised around a command centre for running local and cloud coding agents, including agents from other vendors.