Development

A single-file engine hosts a 744B model on a consumer laptop

development2026-07-12

Claim

A new single-file C engine lets a consumer laptop host the 744-billion-parameter GLM-5.2 by keeping dense layers resident in 25GB of RAM and streaming routed experts off disk on demand.

Reported metric: 744B in 25GB RAM

Reporting date: 2026-07-12 (not necessarily the event date)

Sources

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

Welcome to July 12, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to July 12, 2026

Actor

Z.ai

Evidence for

Supersedes

A 27-billion-parameter model is squeezed onto a phone

Referenced by

Cite or correct this record

Citation formatCitation text

A single-file engine hosts a 744B model on a consumer laptop
Innermost Loop KB — secondary record
Reporting date: 2026-07-12
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-07-12-a-744b-model-hosted-on-a-laptop
Claim: A new single-file C engine lets a consumer laptop host the 744-billion-parameter GLM-5.2 by keeping dense layers resident in 25GB of RAM and streaming routed experts off disk on demand.
Attributed sources:
- Welcome to July 12, 2026 — https://theinnermostloop.substack.com/p/welcome-to-july-12-2026
This citation does not imply independent verification of linked-source claims.

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