Local Ai
v0.30.0-rc18
v0.30.0-rc18 is a pre-release version that changes Ollama's architecture to directly support llama.cpp instead of building on GGML, enabling GGUF file format compatibility. MLX is used to accelerate m
v0.30.0-rc18 is a pre-release version that changes Ollama's architecture to directly support llama.cpp instead of building on GGML, enabling GGUF file format compatibility. MLX is used to accelerate model inference on Apple Silicon. The release invites community feedback on performance, errors, crashes, and memory utilization before the stable version launch.
Source: Ollama Releases | 2026-05-18