1d ago

ExecuTorch Gains MLX Delegate for Running PyTorch Models on Apple Silicon GPUs

——0——
Original post
Awni Hannun#813@AWNIHANNUNOPPyTorchPyTorch@PYTORCH

ExecuTorch now has an MLX delegate that runs PyTorch models on Apple Silicon GPUs. It supports LLMs, speech-to-text, and MoE models with quantization via TorchAO. Export with torch.export, run on Metal. Read our latest blog: https://pytorch.org/blog/running-pytorch-models-on-apple-silicon-gpus-with-the-executorch-mlx-delegate/

9:00 AM · May 18, 2026 View on X
QUOTE POSTAwni Hannun#813Awni Hannun@AWNIHANNUN

This is pretty cool - write PyTorch and export and run with MLX on Apple silicon

PyTorchPyTorch@PyTorch

ExecuTorch now has an MLX delegate that runs PyTorch models on Apple Silicon GPUs. It supports LLMs, speech-to-text, and MoE models with quantization via TorchAO. Export with torch.export, run on Metal. Read our latest blog: https://pytorch.org/blog/running-pytorch-models-on-apple-silicon-gpus-with-the-executorch-mlx-delegate/

4:00 PM · May 18, 2026 · 22.4K Views
2:28 AM · May 20, 2026 · 12.6K Views