Ollama
Run Llama and other large language models locally
- Pricing:
- Free
Overview
Ollama is a command-line tool for running large language models locally. It lets users download and run models such as Llama2, CodeLlama, and others on their own computers, while also supporting customization and the creation of custom models.
This free, open-source project currently supports macOS and Linux, with Windows support planned for the future.
Core capabilities
- Run LLMs locally
- Easily run open-source large language models on your machine
- One-command install
- Simple commands to download and run models
- Multi-model support
- Run Llama, Mistral, Gemma and other models
- API server
- Local REST API for integrating models into applications
- Privacy
- Keep data local with on-device inference
- Cross-platform
- Works on macOS, Linux and Windows
- Model library
- Access a growing library of open-source models
Use cases
- Run Llama 3 locally for intelligent Q&A without an internet connection
- Integrate the Ollama API into a development environment to quickly prototype AI chatbots
- Create domain-specific models with custom Modelfiles to assist internal document retrieval
- Deploy Ollama on a campus network so students can practice prompt engineering and model tuning
- Process text summarization and translation locally with Ollama for enterprise sensitive data scenarios
- Use Ollama as a backend to bring AI capabilities to VS Code extensions or terminal tools
- Distribute Ollama across multiple machines to build a private model cluster
- Leverage Ollama's quantization features to run a 7B model on an older MacBook
Who it's for
AI developers, Machine learning engineers, Tech enthusiasts, Researchers, Enterprise IT teams, Privacy-conscious users, Educators
Getting started
- 1Download and install — Visit the official website, download the installer for your system, and complete the installation
- 2Start a model — Run `ollama run llama3` in the terminal to download and launch the specified model
- 3Chat interactively — After the model starts, type questions directly in the terminal to get real-time answers
- 4Use the API — Access the REST API at `http://localhost:11434` and send requests with curl or a programming language
- 5Create custom models — Write a Modelfile, then run `ollama create mymodel -f ./Modelfile` to create your own model
Traffic analytics
ollama.aiPricing
Free
$0
- For getting started with open models Includes: Run models locally Includes access to starter models Add credits to unlock all models No service fees
Enterprise
Custom
- For larger teams with volume usage pricing Everything in Team, plus: Limit team access to specific models Set cost budgets for users and API keys Private Slack channel with dedicated support Custom security questionnaires
Related tools
DeepSeek R1 OnlineFreeFree, no-login web access to the open-source DeepSeek R1 reasoning model, designed for advanced multi-step inference and outperforming OpenAI o1.
Together AIPaidThe AI Native Cloud: Build, deploy, and scale full-stack AI with inference, fine-tuning, and GPU clusters.
NeuroooFreeNeurooo is your AI-powered translation companion, delivering high-quality, context-aware machine translations in over 100 languages. Built on generalist large language models, it understands idioms, fixes flawed source text, and adapts tone—offering a more natural, European-focused alternative to traditional translation tools.
AnythingLLMFreeYour private, on-device AI assistant that runs entirely on your computer — no accounts, no API keys, and no token limits.
