Development

A 744B open model is shrunk from 1.51TB to 217GB to run locally

development2026-06-19

Claim

Unsloth's guide to running GLM-5.2 locally shrinks the 744B model from 1.51 terabytes to 217 gigabytes, as Artificial Analysis's AA-Briefcase ranked Fable 5 first, Opus 4.8 second and the open GLM-5.2 third on multi-week knowledge work.

Reported metric: 1.51TB to 217GB

Reporting date: 2026-06-19 (not necessarily the event date)

Sources

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

Welcome to June 19, 2026 (theinnermostloop.substack.com)

Knowledge graphopen in browser →

Reported in

Welcome to June 19, 2026

Actor

Evidence for

Supersedes

A Chinese open model takes the lead while the frontier sits unavailable

Referenced by

Cite or correct this record

Citation formatCitation text

A 744B open model is shrunk from 1.51TB to 217GB to run locally
Innermost Loop KB — secondary record
Reporting date: 2026-06-19
KB permalink: https://nicholsn.github.io/innermost-loop-kb/developments/2026-06-19-a-744b-model-shrunk-to-run-locally
Claim: Unsloth's guide to running GLM-5.2 locally shrinks the 744B model from 1.51 terabytes to 217 gigabytes, as Artificial Analysis's AA-Briefcase ranked Fable 5 first, Opus 4.8 second and the open GLM-5.2 third on multi-week knowledge work.
Attributed sources:
- Welcome to June 19, 2026 — https://theinnermostloop.substack.com/p/welcome-to-june-19-2026
This citation does not imply independent verification of linked-source claims.

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