Featured Open Source Trending Beginner Verified

Ollama

Run open models on your own machine with one command.

Ollama reduced local model hosting to `ollama run`. It bundles weights, quantisation and a chat template into a single pullable artefact, exposes an OpenAI-compatible HTTP API on localhost, and handles GPU offload automatically. It is the shortest path from nothing installed to a working local model, which is why so many other projects list it as their default backend.

Go Docker CUDA
1Views
0Likes
0Downloads
0Bookmarks
Source Code
invitationbuddy.com/ai-projects/ollama
O
0GitHub Stars

About This Project

Ollama reduced local model hosting to `ollama run`. It bundles weights, quantisation and a chat template into a single pullable artefact, exposes an OpenAI-compatible HTTP API on localhost, and handles GPU offload automatically. It is the shortest path from nothing installed to a working local model, which is why so many other projects list it as their default backend.

Technology Stack (3)

Go Open-source AI projects built with Go. Docker Open-source AI projects built with Docker. CUDA Open-source AI projects built with CUDA.

Source Code

ollama/ollama Open Source
Go 0 Stars 0 Forks 0 Contributors MIT
View on GitHub Download ZIP

Project Metrics

Total Views1
Downloads0
GitHub Stars0
Avg Rating0.0/5

Project Reviews

No reviews yet — be the first to review this project.

Sign in to write a review.

Sign In