Tuesday, 22 September 2026 @ 02:02 UTC~2214,580172,138

Ollama (Portable)

Ollama·Ollama.Ollama.Portable

Start building with open models.

Get up and running with Kimi-K2.5, GLM-5, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

winget install --id Ollama.Ollama.Portable --exact --source winget

Latest 0.33.1·August 26, 2026

Release Notes

What's Changed

  • MLX: Qwen3.8 Flash Next support
  • cmake: make external compat patches idempotent
  • MLX and llama.cpp update
  • mlxrunner: add structured output support
  • mlxrunner: avoid Metal GPU timeouts when loading models from slow storage Full Changelog: https://github.com/ollama/ollama/compare/v0.33.0...v0.33.1

Installer type: zip

x64—321BF63E36871FB31EE44CF4987150D770C679AC3E233115540D83468D675B06
arm64—BCABA70B98B90EF8B6914358C8F737E5D5CAA6C48D778FCC95D36729EB58237F

Details

Homepage
https://github.com/ollama/ollama
License
MIT
Publisher
Ollama
Support
https://github.com/ollama/ollama/issues
Copyright
Copyright (c) Ollama

Tags

deepseekgemmagemma3glmgogolanggpt-ossllamallama3llmllmsminimaxmistralollamaqwen

Older versions (2)

0.32.5
x64—7C941AE084569D298062D29F8139163A3187C76DBCA0479C70D085E78FD8C7BB
arm64—F7CF76916C24550033500A92FB56B3CE3D225F3D7CDE0CE0438E62696B34507A
0.20.2
x64—F26EAD8BAA55E919828FFE88CDDF3E588444891E43E19A059F1D6C933FB1A5B6
arm64—E4D2111AA2B1BED7768B0DD20C17BC7D2860F0EE7B8C78BFFCA5920504419291