●Change8

v0.30.0-rc27

📦 ollamaView on GitHub →
✨ 3 features

Summary

This pre-release updates the architecture to directly support llama.cpp and the GGUF format, while introducing MLX acceleration for Apple Silicon inference. Feedback is requested on performance and stability.

Migration Steps

  1. When installing on Mac/Linux, use OLLAMA_VERSION=0.30.0-rc27 in the install script.
  2. When installing on Windows, set $env:OLLAMA_VERSION="0.30.0-rc27" before running the install script.

✨ New Features

  • Architecture changed to directly support llama.cpp instead of building on top of GGML.
  • Added compatibility with GGUF file format.
  • MLX is now used to accelerate model inference on Apple Silicon.