Apple Silicon path
Install quickstart
This is the app-first path for technical Mac users. It does not require cloning a repository or building from source.
What you need
- A Mac with Apple Silicon and enough free disk space for a model artifact and runtime files.
- A current InferGrade Hub browser session.
- The Desktop Runner DMG provided by the InferGrade release or beta invitation.
- Hugging Face access only when you choose a gated or private artifact. Public models do not require it.
1. Install Desktop Runner
- Open the InferGrade Runner DMG.
- Drag InferGrade Runner into Applications.
- Launch the app and allow macOS to open it if Gatekeeper asks for confirmation.
- Keep the app open while you pair and run the first benchmark.
2. Pair the Runner
- Open Hub Setup.
- Sign in, then create a one-time pairing code.
- Paste the code into Desktop Runner.
- Wait for Hub Setup to show the paired Runner as ready.
3. Install or select the runtime
- In Desktop Runner, install or select the managed llama.cpp Metal runtime.
- Use the Runner self-test before starting a benchmark.
- If runtime setup fails, use the support export and recovery guidance before retrying.
4. Queue one known-good run
- In Hub Recommend, choose a known-good question or open a public Result follow-up.
- Use Build to prepare one local run from that recommendation.
- Queue the run and keep Desktop Runner open so it can claim, execute, and upload.
- Open the Result page to inspect what the run proves, what it does not prove, and the next benchmark.
If something blocks
- Pairing code expired or already used: create a fresh code in Hub Setup. Do not paste old codes into issues, chats, or screenshots.
- Runner token revoked or expired: unpair in Desktop Runner, then pair again with a new Hub code.
- Runtime setup failed: retry the managed runtime install, select an existing llama.cpp binary, or create a support export before changing paths.
- Model path missing or gated: choose a local GGUF file or reconnect Hugging Face access, then run the self-test again.
- Upload rejected after a local run: keep the local artifacts, do not edit run ids by hand, and use the support export for recovery.