Download Latest Version ollama-linux-arm64-jetpack6.tgz (367.8 MB)
Email in envelope

Get an email when there's a new version of Ollama

Home / v0.12.10
Name Modified Size InfoDownloads / Week
Parent folder
Ollama.dmg 2025-11-06 49.5 MB
OllamaSetup.exe 2025-11-06 1.2 GB
ollama-linux-arm64.tgz 2025-11-06 2.0 GB
ollama-linux-arm64-jetpack6.tgz 2025-11-06 365.4 MB
ollama-linux-arm64-jetpack5.tgz 2025-11-06 461.5 MB
ollama-linux-amd64-rocm.tgz 2025-11-06 1.3 GB
ollama-linux-amd64.tgz 2025-11-06 1.9 GB
ollama-darwin.tgz 2025-11-06 26.7 MB
ollama-windows-arm64.zip 2025-11-06 22.2 MB
ollama-windows-amd64.zip 2025-11-06 1.9 GB
ollama-windows-amd64-rocm.zip 2025-11-06 371.7 MB
Ollama-darwin.zip 2025-11-06 49.5 MB
sha256sum.txt 2025-11-06 1.1 kB
README.md 2025-11-05 1.3 kB
v0.12.10 source code.tar.gz 2025-11-05 21.1 MB
v0.12.10 source code.zip 2025-11-05 21.7 MB
Totals: 16 Items   9.6 GB 183

ollama run now works with embedding models

ollama run can now run embedding models to generate vector embeddings from text:

ollama run embeddinggemma "Hello world"

Content can also be provided to ollama run via standard input:

echo "Hello world" | ollama run embeddinggemma

What's Changed

  • Fixed errors when running qwen3-vl:235b and qwen3-vl:235b-instruct
  • Enable flash attention for Vulkan (currently needs to be built from source)
  • Add Vulkan memory detection for Intel GPU using DXGI+PDH
  • Ollama will now return tool call IDs from the /api/chat API
  • Fixed hanging due to CPU discovery
  • Ollama will now show login instructions when switching to a cloud model in interactive mode
  • Fix reading stale VRAM data
  • ollama run now works with embedding models

New Contributors

Full Changelog: https://github.com/ollama/ollama/compare/v0.12.9...v0.12.10

Source: README.md, updated 2025-11-05