v0.40.21411543.6 MB
MIT
strict
core24
Get up and running with large language models, locally.
Ollama – Local AI Model Runner
Run, manage, and switch between a wide range of open‑source LLMs directly on your local machine. Ollama provides fast, offline inference with a simple CLI and API, ensuring your data never leaves the device. Ideal for developers, researchers, and anyone who wants powerful AI without cloud dependencies.
Run, manage, and switch between a wide range of open‑source LLMs directly on your local machine. Ollama provides fast, offline inference with a simple CLI and API, ensuring your data never leaves the device. Ideal for developers, researchers, and anyone who wants powerful AI without cloud dependencies.
Update History
v0.34.0 (137) → v0.40.2 (141)22 Oct 2026, 23:15 UTC
v0.33.3 (134) → v0.34.0 (137)18 Sept 2026, 06:00 UTC
v0.32.14 (131) → v0.33.3 (134)15 Sept 2026, 08:45 UTC
v0.32.5 (128) → v0.32.14 (131)20 Aug 2026, 15:15 UTC
v0.30.10 (126) → v0.32.5 (128)5 Aug 2026, 09:00 UTC
v0.24.0 (122) → v0.30.10 (126)4 Aug 2026, 10:00 UTC
v0.19.0 (116) → v0.24.0 (122)20 May 2026, 08:15 UTC
v0.18.0 (112) → v0.19.0 (116)3 May 2026, 05:15 UTC
v0.17.4 (109) → v0.18.0 (112)18 Mar 2026, 13:33 UTC
v0.15.1 (105) → v0.17.4 (109)10 Mar 2026, 21:01 UTC
9 Feb 2024, 19:35 UTC
13 Oct 2026, 03:10 UTC
13 Dec 2025, 09:47 UTC