v0.30.0-rc32
Breaking Changes📦 ollamaView on GitHub →
⚠ 1 breaking✨ 3 features🐛 1 fixes🔧 5 symbols
Summary
This release transitions Ollama's architecture to directly support llama.cpp, enabling GGUF compatibility and MLX acceleration on Apple Silicon. A known issue is that `nomic-embed-text` now enforces lowercase input.
⚠️ Breaking Changes
- The underlying architecture has changed from using GGML to directly supporting llama.cpp, which may affect custom integrations or scripts relying on the previous internal structure.
Migration Steps
- Users installing on Mac/Linux should use the provided curl command specifying OLLAMA_VERSION=0.30.0-rc31.
- Users installing on Windows should use the provided PowerShell commands specifying OLLAMA_VERSION="0.30.0-rc31".
✨ New Features
- Direct support for llama.cpp architecture.
- Compatibility with the GGUF file format.
- MLX acceleration for model inference on Apple Silicon.
🐛 Bug Fixes
- The `nomic-embed-text` model now correctly converts inputs to lowercase as specified by the model card, fixing prior behavior that incorrectly preserved mixed case.