Ollama 0.30 adds llama.cpp-based GGUF compatibility to its MLX engine
In 0.30, added llama.cpp-based GGUF compatibility to its MLX engine
Why it matters
The local deployment stack reorganized from sole reliance on llama.cpp to MLX first + GGUF compatibility
Source — Primary sources first; secondary reports are labelled “Press”
Officialollama.comhttps://ollama.com/blogAdded in Week 35, 2026 · See that week