Change8

v0.20.4-rc2

📦 ollamaView on GitHub →
2 features🐛 1 fixes🔧 2 symbols

Summary

This release focuses on performance improvements for MLX (M5 with NAX) and Gemma4 (flash attention), alongside minor fixes for model creation.

✨ New Features

  • Improve M5 performance with NAX for MLX backend.
  • Enable flash attention for Gemma4 models.

🐛 Bug Fixes

  • Clean up experimental paths and fix creation from existing safetensor models.

Affected Symbols