v0.16.3
📦 ollamaView on GitHub →
✨ 5 features🐛 3 fixes🔧 1 symbols
Summary
This release introduces support for several new model architectures (Gemma 3, Llama 3, Qwen 3) in mlxrunner and adds the new `ollama launch` CLI command. Several minor bug fixes related to mlx model display and scheduling were also implemented.
✨ New Features
- Added support for Gemma 3 architecture in mlxrunner.
- Added support for Llama 3 architecture in mlxrunner.
- Added support for Qwen 3 model in mlxrunner.
- Introduced `ollama launch` command line interface (CLI).
- The `ollama launch` command now always displays the model picker.
🐛 Bug Fixes
- Fixed incorrect display of parameter count in mlx for `ollama show`.
- Added missing linear layer factory.
- Improved mlx model scheduling.