Add measured Apple M5 Max performance

b132651 verified 4 days ago

1.63 kB

license: apache-2.0
tags:
  - ardy
  - motion-generation
  - macos
  - apple-silicon
  - mps
  - pytorch

ARDY on Apple Silicon

Open-source macOS compatibility tools for running NVIDIA ARDY locally through PyTorch Metal (MPS). This repository does not contain or redistribute model weights.

Watch the Mac/MPS demo

How it works

Download the official ARDY source.
Run the ardy-macos-tools installer on an Apple Silicon Mac.
Accept Meta Llama 3 access and authenticate with Hugging Face.
ARDY downloads its official checkpoint and text-encoder weights directly.
The compatibility service runs generation through Apple's MPS backend.

The installer, source code, checksums, and complete instructions live in the GitHub project. Model files, caches, tokens, and the PocketAI application are not included.

Measured Mac performance

In two desktop sessions on an Apple M5 Max with 128 GB unified memory, a four-second, 80-frame motion generated in 1.90–3.62 seconds after the models were resident. Peak MPS driver allocation was 15.23 GiB. Cached cold loading took 145.6–260.3 seconds and varied with desktop conditions.

See the full reproducible benchmark for individual runs, CPU measurements, methodology, and caveats.

Built with Meta Llama 3. ARDY checkpoints remain subject to the NVIDIA Open Model Agreement. See the project's third-party notices before use.