Ollama v0.30.0-rc23: "directly support llama.cpp" & "compatibility with GGUF"

Ollama released version 0.30.0-rc23, a pre-release that shifts the software's architecture to directly support llama.cpp instead of building on top of GGML, and adds compatibility with the GGUF file format. The update also integrates MLX to accelerate model inference on Apple Silicon. The pre-release does not yet support the `laguna-xs.2` and `llama3.2-vision` models.

v0.30.0 Pre-release Pre-release github-actions /apps/github-actions released this · 2 commits /ollama/ollama/compare/v0.30.0-rc23...main to main since this releaseThis version of Ollama will change the architecture to directly support llama.cpp instead of building on top of GGML, and allows for compatibility with GGUF file format. MLX is used to accelerate model inference on Apple Silicon. While in pre-release we'd love feedback https://github.com/ollama/ollama/pull/16031 on: - Performance improvements or degradation - Errors or crashes that did not previously occur - Memory utilization improvements or degradation Known issues: laguna-xs.2 is not supported yet on this pre-release llama3.2-vision is not supported yet on this pre-release Installing: Mac/Linux curl -fsSL https://ollama.com/install.sh | OLLAMA VERSION=0.30.0-rc23 sh Windows $env:OLLAMA VERSION="0.30.0-rc23"; irm https://ollama.com/install.ps1 | iex