Local Ai
v0.30.1
Ollama 0.30 provides improved compatibility and performance using llama.cpp, augments the MLX engine on Apple Silicon for broader hardware support, and brings support for a wider range of models inclu
Ollama 0.30 provides improved compatibility and performance using llama.cpp, augments the MLX engine on Apple Silicon for broader hardware support, and brings support for a wider range of models including GGUF-based models from Hugging Face and fine-tuned models along with faster NVIDIA hardware performance. The release includes Gemma 4 tool calling support, allowing models to use external tools.
Source: Ollama Releases | 2026-06-02