Developers building long-horizon agentic pipelines can now launch Kimi K2.6's multi-agent system directly from Ollama, while MLX users benefit from faster sampling and tokenization without any configuration changes.
Developers on Apple Silicon can now run Gemma 4 locally with MLX acceleration, while the expanded `ollama launch` ecosystem makes it easier to wire up agentic coding tools like Hermes and GitHub Copilot CLI in a single command.