ollama/ollama
Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
Ollama helps individuals and teams set up and interact with various open-source large language models (LLMs) on their own computers. You can input text prompts or data, and the models generate responses, code, or perform other AI-powered tasks. It's designed for developers, researchers, or anyone interested in experimenting with, integrating, or building applications using local LLMs.
164,987 stars. Actively maintained with 117 commits in the last 30 days.
Use this if you want to run powerful AI models like Kimi-K2.5, Gemma, or Qwen directly on your computer, without relying on external cloud services.
Not ideal if you prefer a fully managed, cloud-based AI service or don't have the technical comfort to install and manage software locally.
Stars
164,987
Forks
14,940
Language
Go
License
MIT
Category
Last pushed
Mar 13, 2026
Commits (30d)
117
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/ollama/ollama"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Recent Releases
Related tools
jd-opensource/JDOxyGent4J
JDOxyGent4J: The Java sibling of the OxyGent ecosystem.
sammcj/gollama
Go manage your Ollama models
dext7r/ollama-api-pool
๐ Intelligent Ollama API proxy pool based on Cloudflare Workers - ๅบไบ Cloudflare Workers ็ๆบ่ฝ...
ollama4j/ollama4j-web-ui
Web UI for Ollama built in Java with Vaadin, Spring Boot and Ollama4j
g1ibby/ollama-auth
This project provides a Docker image for running the Ollama service with basic authentication...