Back
ALeeXSD @ALeeXSD
Ollama: Get Up and Running with Large Language Models Locally
GitHubRun LLaMA, DeepSeek, Mistral, and Qwen locally on macOS, Linux, and Windows with hardware acceleration and an OpenAI-compatible REST API.
Also available in:RU
Ollama is the leading open-source project (over 105,000 GitHub stars) enabling developers to download, customize, and run open LLMs locally with a single terminal command.
Key Highlights
- Zero-Friction Execution: easily pull and serve state-of-the-art models including LLaMA 3, DeepSeek-R1, Mistral, and Qwen.
- Hardware Acceleration: automatic GPU offloading for Apple Silicon (Metal), NVIDIA CUDA, and AMD ROCm.
- OpenAI API Compatibility: exposes standard…
ollamalocal-llmaigo
Versions
Versions and changelog are tracked in the GitHub repository.
License terms
MIT
Install command
curl -fsSL https://ollama.com/install.sh | sh
Version
0.5.11
Comments · 0
Nothing here yet
Sign in to participate