v0.30.9

parruda/swarmv0.30.9Jun 15, 2026by github-actions[bot]

AI Summary

Expands model support with Cohere2Moe architecture and fixes parser/rendering issues, while adding safeguards for large message context windows.

Key Highlights

  • Support for Cohere2Moe architecture
  • Fix for LFM2 parser when thinking is not emitted
  • Error handling for single messages exceeding context window

New Features

  • Cohere2Moe architecture support
  • LFM2 parser/render fixes for missing thinking emission
  • Context window validation returning errors for large messages

Full Release Notes

## What's Changed
* Support for Cohere2Moe architecture
* Fixed LFM2 parser/render for cases where thinking was not emitted
* Fixed issue where `ollama launch claude` and other coding agent or assistant use cases would only output one token
* Ollama will now return an error if a single message is larger than the current context window

**Full Changelog**: https://github.com/ollama/ollama/compare/v0.30.8...v0.30.9-rc1