Download Latest Version
ollama-linux-arm64-jetpack6.tgz (365.4 MB)
Get an email when there's a new version of Ollama
| Name | Modified | Size | Downloads / Week |
|---|---|---|---|
| Parent folder | |||
| Ollama.dmg | 2025-10-29 | 48.4 MB | |
| OllamaSetup.exe | 2025-10-29 | 1.2 GB | |
| ollama-linux-arm64.tgz | 2025-10-29 | 2.0 GB | |
| ollama-darwin.tgz | 2025-10-29 | 25.6 MB | |
| Ollama-darwin.zip | 2025-10-29 | 48.3 MB | |
| ollama-linux-amd64-rocm.tgz | 2025-10-29 | 1.3 GB | |
| ollama-linux-amd64.tgz | 2025-10-29 | 1.9 GB | |
| ollama-linux-arm64-jetpack5.tgz | 2025-10-29 | 461.6 MB | |
| ollama-linux-arm64-jetpack6.tgz | 2025-10-29 | 365.4 MB | |
| ollama-windows-amd64-rocm.zip | 2025-10-29 | 356.9 MB | |
| ollama-windows-amd64.zip | 2025-10-29 | 1.9 GB | |
| ollama-windows-arm64.zip | 2025-10-29 | 22.2 MB | |
| sha256sum.txt | 2025-10-29 | 1.1 kB | |
| README.md | 2025-10-29 | 2.3 kB | |
| v0.12.7 source code.tar.gz | 2025-10-29 | 20.3 MB | |
| v0.12.7 source code.zip | 2025-10-29 | 20.8 MB | |
| Totals: 16 Items | 9.6 GB | 20 | |
New models
- Qwen3-VL: Qwen3-VL is now available in all parameter sizes ranging from 2B to 235B
- MiniMax-M2: a 230 Billion parameter model built for coding & agentic workflows available on Ollama's cloud
Add files and adjust thinking levels in Ollama's new app
Ollama's new app now includes a way to add one or many files when prompting the model:
For better responses, thinking levels can now be adjusted for the gpt-oss models:
New API documentation
New API documentation is available for Ollama's API: https://docs.ollama.com/api
What's Changed
- Model load failures now include more information on Windows
- Fixed embedding results being incorrect when running
embeddinggemma - Fixed gemma3n on Vulkan backend
- Increased time allocated for ROCm to discover devices
- Fixed truncation error when generating embeddings
- Fixed request status code when running cloud models
- The OpenAI-compatible
/v1/embeddingsendpoint now supportsencoding_formatparameter - Ollama will now parse tool calls that don't conform to
{"name": name, "arguments": args}(thanks @rick-github!) - Fixed prompt processing reporting in the llama runner
- Increase speed when scheduling models
- Fixed issue where
FROM <model>would not inheritRENDERERorPARSERcommands
New Contributors
- @npardal made their first contribution in https://github.com/ollama/ollama/pull/12715
Full Changelog: https://github.com/ollama/ollama/compare/v0.12.6...v0.12.7-rc0
