Development

Apple reorganizes its pro silicon around running models locally

development2026-03-04

Claim

Apple's M5 Pro and M5 Max bond two third-generation 3-nm dies with neural accelerators embedded inside every GPU core and four times the AI performance of M4, a design read as reorganizing silicon around the assumption that a pro laptop's primary workload is running language models.

Reported metric: 4x M4

Reporting date: 2026-03-04 (not necessarily the event date)

Sources

Attribution and reporting linked by this record; links do not imply independent verification.

Welcome to March 4, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to March 4, 2026

Actor

Apple

Evidence for

Supersedes

Apple uses a tenth of the compute it spent $4.5B building

Referenced by

Cite or correct this record

Citation formatCitation text

Apple reorganizes its pro silicon around running models locally
Innermost Loop KB — secondary record
Reporting date: 2026-03-04
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-03-04-apple-reorganizes-silicon-around-transformers
Claim: Apple's M5 Pro and M5 Max bond two third-generation 3-nm dies with neural accelerators embedded inside every GPU core and four times the AI performance of M4, a design read as reorganizing silicon around the assumption that a pro laptop's primary workload is running language models.
Attributed sources:
- Welcome to March 4, 2026 — https://theinnermostloop.substack.com/p/welcome-to-march-4-2026
This citation does not imply independent verification of linked-source claims.

Suggest a correction — opens a GitHub draft for you to review and submit.