Ollama
by ollama
Run large models locally with a single command — LLMs, vision, and embeddings on any machine.
Get the code
# Clone the repositorygit clone https://github.com/ollama/ollama
About Ollama
Ollama bundles model weights, configs, and a Modelfile format so you can run models like Llama, Qwen, Gemma, and DeepSeek locally on macOS, Linux, and Windows, with an OpenAI-compatible API and a growing app ecosystem.
Frequently asked questions
What is Ollama?
Ollama bundles model weights, configs, and a Modelfile format so you can run models like Llama, Qwen, Gemma, and DeepSeek locally on macOS, Linux, and Windows, with an OpenAI-compatible API and a growing app ecosystem.
Is Ollama safe to use?
Ollama is an open-source project by ollama on GitHub. Review the source code and license before using it in production.
How do I get started with Ollama?
git clone https://github.com/ollama/ollama
What language is Ollama written in?
openSource.faqWhatLanguageAnswer
Related projects
LLM inference in C/C++ with quantization — runs models on CPU, GPU, and edge devices.
High-throughput, memory-efficient inference and serving engine for LLMs with PagedAttention.
AI gateway to call 100+ LLM APIs in OpenAI format with cost tracking, guardrails, and load balancing.