| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| Ollama.dmg | 2025-12-12 | 59.7 MB | |
| OllamaSetup.exe | 2025-12-12 | 1.3 GB | |
| ollama-linux-arm64.tgz | 2025-12-12 | 2.1 GB | |
| ollama-linux-arm64-jetpack6.tgz | 2025-12-12 | 374.9 MB | |
| ollama-linux-arm64-jetpack5.tgz | 2025-12-12 | 475.1 MB | |
| ollama-linux-amd64.tgz | 2025-12-12 | 2.0 GB | |
| ollama-linux-amd64-rocm.tgz | 2025-12-12 | 1.3 GB | |
| ollama-darwin.tgz | 2025-12-12 | 27.6 MB | |
| ollama-windows-arm64.zip | 2025-12-12 | 22.3 MB | |
| ollama-windows-amd64.zip | 2025-12-12 | 2.0 GB | |
| ollama-windows-amd64-rocm.zip | 2025-12-12 | 376.9 MB | |
| Ollama-darwin.zip | 2025-12-12 | 59.7 MB | |
| sha256sum.txt | 2025-12-12 | 1.1 kB | |
| README.md | 2025-12-12 | 917 Bytes | |
| v0.13.3 source code.tar.gz | 2025-12-12 | 20.9 MB | |
| v0.13.3 source code.zip | 2025-12-12 | 21.6 MB | |
| Totals: 16 Items | 10.2 GB | 86 | |
New models
- Devstral-Small-2: 24B model that excels at using tools to explore codebases, editing multiple files and power software engineering agents.
- rnj-1: Rnj-1 is a family of 8B parameter open-weight, dense models trained from scratch by Essential AI, optimized for code and STEM with capabilities on par with SOTA open-weight models.
- nomic-embed-text-v2: nomic-embed-text-v2-moe is a multilingual MoE text embedding model that excels at multilingual retrieval.
What's Changed
- Improved truncation logic when using
/api/embedand/v1/embeddings - Extend Gemma 3 architecture to support rnj-1 model
- Fix error that would occur when running qwen2.5vl with image input
Full Changelog: https://github.com/ollama/ollama/compare/v0.13.2...v0.13.3