Name | Modified | Size | Downloads / Week |
---|---|---|---|
Parent folder | |||
Ollama.dmg | 2025-09-23 | 47.9 MB | |
OllamaSetup.exe | 2025-09-23 | 1.2 GB | |
ollama-linux-arm64.tgz | 2025-09-23 | 1.9 GB | |
ollama-linux-arm64-jetpack6.tgz | 2025-09-23 | 359.6 MB | |
ollama-linux-arm64-jetpack5.tgz | 2025-09-23 | 450.2 MB | |
ollama-linux-amd64.tgz | 2025-09-23 | 1.9 GB | |
ollama-linux-amd64-rocm.tgz | 2025-09-23 | 1.1 GB | |
ollama-darwin.tgz | 2025-09-23 | 25.1 MB | |
ollama-windows-arm64.zip | 2025-09-23 | 22.1 MB | |
Ollama-darwin.zip | 2025-09-23 | 47.8 MB | |
ollama-windows-amd64-rocm.zip | 2025-09-23 | 257.5 MB | |
ollama-windows-amd64.zip | 2025-09-23 | 1.9 GB | |
sha256sum.txt | 2025-09-23 | 1.1 kB | |
README.md | 2025-09-23 | 617 Bytes | |
v0.12.1 source code.tar.gz | 2025-09-23 | 11.0 MB | |
v0.12.1 source code.zip | 2025-09-23 | 11.4 MB | |
Totals: 16 Items | 9.3 GB | 48 |
New models
- Qwen3 Embedding: state of the art open embedding model by the Qwen team
What's Changed
- Qwen3-Coder now supports tool calling
- Ollama's app will now longer show "connection lost" in error when connecting to cloud models
- Fixed issue where Gemma3 QAT models would not output correct tokens
- Fix issue where
&
characters in Qwen3-Coder would not be parsed correctly when function calling - Fixed issues where
ollama signin
would not work properly on Linux
Full Changelog: https://github.com/ollama/ollama/compare/v0.12.0...v0.12.1