ollama
SHA-256Ollama lets you download, run, and manage large language models locally. One command, multiple platforms, endless possibilities.
Smart Download
Download Download Version
v0.23.3 · 2 GB
Run any open-source LLM locally with a single command. Insanely simple.
Core Features
- One-line install on macOS, Windows, Linux, and Docker
- Built-in model library with Gemma3, Llama, and more
- REST API and Python/JS libraries for integration
- Interactive chat via `ollama run <model>`
- Seamless integration with editors, IDEs, and AI assistants
What It Can't Do
- •Requires decent hardware (16GB+ RAM recommended; GPU helps performance). First model download needs internet and several GB. Local inference is slower than cloud but ensures privacy.
Use Cases
- Run open-source LLMs locally for Q&A, translation, code generation
- Backend for custom chatbots or automation tools
- Compare and test different models for development
Ollama is an open-source tool that lets you download, run, and manage large language models (like Gemma3, Llama, etc.) on your own machine. It provides a simple command-line interface, a REST API, and Python/JavaScript libraries for easy integration. With one-line installers for all major platforms and Docker, you can start chatting with models immediately. The project also supports plugging into popular editors (VS Code, Emacs) and AI assistants, making it a versatile local AI hub. Thousands of community integrations extend its capabilities.
Tags
Getting Started
Download installer
Click the button above to download the installer for your system
Install the software
Double-click the downloaded installer and follow the prompts
Step 1: Download from ollama.com or run one-liner (macOS/Linux: curl -fsSL https://ollama.com/install.sh | sh; Windows: irm https://ollama.com/install.ps1 | iex)
Step 2: Type `ollama run gemma3` (or any model) to download and start chatting
Step 3: Ask questions or use `ollama launch claude` for integrated tools
- Step 1: Download from ollama.com or run one-liner (macOS/Linux: curl -fsSL https://ollama.com/install.sh | sh; Windows: irm https://ollama.com/install.ps1 | iex)
- Step 2: Type `ollama run gemma3` (or any model) to download and start chatting
- Step 3: Ask questions or use `ollama launch claude` for integrated tools
SHA-256 checksum verified
Checksum extracted from GitHub official Release page
SHA256 Checksum
f35ee7f9e0cc53a6d2d9603e82d0b56be207c85e109a14a3a498aedbdb1417d7This checksum is extracted from the GitHub Release page. Verify file integrity after download.
All SHA-256 checksums on this platform are extracted from the project's official GitHub Release page, without any modification. You can independently verify them on the GitHub Releases page.
Open Source Transparency
View GitHub SourceUninstall Info
macOS: Delete /Applications/Ollama.app; Linux: sudo rm /usr/local/bin/ollama; Windows: Uninstall via Add/Remove Programs.
No Extra Dependencies
Ready to use after download. No additional runtime required.
Having issues? Check the FAQ below
5 FAQs
Similar Projects
llama.cpp
High-performance LLM inference engine in C/C++ with minimal dependencies, supporting quantized models (1.5–8 bit) and diverse hardware (Apple Silicon, CUDA, Vulkan, etc.).
mempalace
Open-source local-first AI memory system with verbatim storage and semantic search — zero API calls, no keys, top benchmark scores.
ComfyUI
ComfyUI is a modular AI engine with a node-based graph interface for generating images, video, 3D models, and audio. Unlike traditional webui tools, it gives pixel-level control over every model and parameter, making it the preferred choice for professionals.