Download Latest Version
ollama-linux-arm64-jetpack6.tgz (359.6 MB)
Get an email when there's a new version of Ollama
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| ollama-linux-arm64-jetpack6.tgz | 2025-09-25 | 359.6 MB | |
| ollama-windows-arm64.zip | 2025-09-25 | 22.1 MB | |
| ollama-darwin.tgz | 2025-09-25 | 25.1 MB | |
| Ollama-darwin.zip | 2025-09-25 | 47.8 MB | |
| ollama-linux-amd64-rocm.tgz | 2025-09-25 | 1.1 GB | |
| ollama-linux-amd64.tgz | 2025-09-25 | 1.9 GB | |
| ollama-linux-arm64-jetpack5.tgz | 2025-09-25 | 450.2 MB | |
| ollama-linux-arm64.tgz | 2025-09-25 | 1.9 GB | |
| ollama-windows-amd64-rocm.zip | 2025-09-25 | 257.5 MB | |
| ollama-windows-amd64.zip | 2025-09-25 | 1.9 GB | |
| Ollama.dmg | 2025-09-25 | 47.9 MB | |
| OllamaSetup.exe | 2025-09-25 | 1.2 GB | |
| sha256sum.txt | 2025-09-25 | 1.1 kB | |
| README.md | 2025-09-24 | 399 Bytes | |
| v0.12.2 source code.tar.gz | 2025-09-24 | 11.0 MB | |
| v0.12.2 source code.zip | 2025-09-24 | 11.4 MB | |
| Totals: 16 Items | 9.3 GB | 43 | |
What's Changed
- Models with Qwen3's architecture including MoE now run in Ollama's new engine
- Fixed issue where built-in tools for gpt-oss were not being rendered correctly
- Support multi-regex pretokenizers in Ollama's new engine
- Ollama's new engine can now load tensors by matching a prefix or suffix
Full Changelog: https://github.com/ollama/ollama/compare/v0.12.1...v0.12.2