Local Ai
v0.30.0-rc24
v0.30.0-rc24 is a pre-release version that changes Ollama's architecture to directly support llama.cpp instead of building on top of GGML, enabling compatibility with the GGUF file format. MLX is used
v0.30.0-rc24 is a pre-release version that changes Ollama's architecture to directly support llama.cpp instead of building on top of GGML, enabling compatibility with the GGUF file format. MLX is used to accelerate model inference on Apple Silicon. During pre-release testing, feedback is being collected on performance, errors, crashes, and memory utilization.
Source: Ollama Releases | 2026-05-24