Development

A 400-billion-parameter model runs on a phone

development2026-03-24

Claim

The ANEMLL open source project ran a 400-billion-parameter model on an iPhone 17 Pro at 0.6 tokens per second.

Reported metric: 400B on a phone

Reporting date: 2026-03-24 (not necessarily the event date)

Sources

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

Welcome to March 24, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to March 24, 2026

Actor

Apple

Evidence for

Supersedes

An architecture scales to a hundred million tokens with under 9% loss

Referenced by

Cite or correct this record

Citation formatCitation text

A 400-billion-parameter model runs on a phone
Innermost Loop KB — secondary record
Reporting date: 2026-03-24
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-03-24-400b-model-on-a-phone
Claim: The ANEMLL open source project ran a 400-billion-parameter model on an iPhone 17 Pro at 0.6 tokens per second.
Attributed sources:
- Welcome to March 24, 2026 — https://theinnermostloop.substack.com/p/welcome-to-march-24-2026
This citation does not imply independent verification of linked-source claims.

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