← Friday, October 16, 2026InferenceDeep dive

ExecuTorch runs TinyML models on Cortex-M with under 90 KiB of RAM

pytorch.org 9 min read Editor score 8/10

The Cortex-M backend runs four MLPerf Tiny models on an Alif Ensemble E8 in 21.5 ms or less, using under 90 KiB of RAM; the core runtime is under 20 KiB of flash. This shows a single PyTorch workflow can reach tightly constrained devices without a framework conversion step.

What: - ExecuTorch's Cortex-M backend runs PyTorch models directly on Arm Cortex-M CPUs, without conversion to another framework format.
How: - Ahead-of-time passes replace operators with CMSIS-NN-backed kernels; compile-time CPU and ISA selection avoids runtime dispatch.
Why it matters: - For embedded AI, four MLPerf Tiny models ran in 21.5 ms or less using under 90 KiB of RAM on one Cortex-M55 core.

The compilation path quantizes PyTorch models and lowers them to Cortex-M kernels. Sketched from the article's own text.

Read on pytorch.org →

Discussion

Discussion is not switched on yet. Use Note above to keep your own thoughts on this story.

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.