●Change8

v0.30.0-rc22

Breaking Changes
📦 ollamaView on GitHub →
⚠ 1 breaking✨ 3 features

Summary

This pre-release updates the core architecture to directly support llama.cpp, enabling GGUF compatibility and leveraging MLX for Apple Silicon acceleration. Users are encouraged to provide feedback on performance and stability.

⚠️ Breaking Changes

  • The underlying architecture has changed from building on GGML to directly supporting llama.cpp, which may affect custom integrations or tooling relying on the previous internal structure.

Migration Steps

  1. When installing on Mac/Linux, use OLLAMA_VERSION=0.30.0-rc21 in the install script: curl -fsSL https://ollama.com/install.sh | OLLAMA_VERSION=0.30.0-rc21 sh
  2. When installing on Windows, set the environment variable OLLAMA_VERSION="0.30.0-rc21" before running the install script: $env:OLLAMA_VERSION="0.30.0-rc21"; irm https://ollama.com/install.ps1 | iex

✨ New Features

  • Direct support for llama.cpp architecture.
  • Compatibility with the GGUF file format is now supported.
  • MLX is used to accelerate model inference on Apple Silicon.