v0.17.1
📦 ollamaView on GitHub →
✨ 3 features🐛 3 fixes🔧 2 symbols
Summary
This release introduces support for the Nemotron architecture and includes several performance and stability improvements, particularly around MLX memory usage and logging. It also updates the mlx-c bindings.
Migration Steps
- Update mlx-c bindings to version 0.5.0.
✨ New Features
- Added support for the Nemotron model architecture.
- Implemented capability-based detection for web search in the UI.
- Added an upgrade configuration option to the settings page in the application.
🐛 Bug Fixes
- Reduced excessive MLX memory usage.
- Fixed duplicate log prefixes and reduced log noise in mlxrunner.
- Prevented defaulting to affine quantization for unquantized models in MLX.