§ local-llm · storyline

Ollama v0.20.4

Ollama releases v0.20.4 with improved M5 performance via NAX on MLX and flash attention enabled for Gemma 4 models.

Apr 7 · 19:57:51 · primary fetch1 sourceupdated Apr 7 · 19:57:51

What's Changed mlx: Improve M5 performance with NAX gemma4: enable flash attention Full Changelog: https://github.com/ollama/ollama/compare/v0.20.3...v0.20.4

read full article on github.com ↗

§ sources1 publication · timeline below

github.comollama v0.20.4primary19:57:51