克隆仓库后运行 swift build -c release，执行 .build/release/TurboFieldfareMac，点击 Download 获取模型，随后点击 Load Model 并 Generate。首次模型安装需要从 Hugging Face 获取模型，该过程需要一定的编程基础。
核验依据
README: TurboFieldfare runs the instruction-tuned **[Gemma 4 26B-A4B](https://ai.google.dev/gemma/docs/core/model_card_4)** without loading the entire 14.3 GB model into memory.
README: When the app opens, choose **Download** and let TurboFieldfare fetch and repack the pinned model (about 15 GB).
README: TurboFieldfare is an independent research project. It is not affiliated with, sponsored by, or endorsed by Google.
README: The CLI uses an existing `.gturbo` installation. If you installed the model through the Mac app, it is already available at `scratch/gemma4.gturbo`.
README: It listens on `http://127.0.0.1:8080/v1` and supports Chat Completions, streaming, function tools, and single-prefix prompt reuse.