Blog / Model guides

Pre-release. Updated when the weights land.

GLM-5.3 open weights: expected release date and what you will need to run it

Published 2026-08-21 ยท This page will be updated in place with measured numbers once the weights are out

Expected around August 28
Z.ai launched GLM-5.3 on August 14, 2026 and says the open weights follow about two weeks later, after its safety evaluation completes. That points to late August. It is an estimate from their stated window, not an announced date.

What GLM-5.3 is

GLM-5.3 is Z.ai's latest flagship, launched on August 14, 2026 on their API and coding plan. Z.ai says it keeps the same base model as GLM-5.2, with the capability gains coming from scaled-up post-training. Their headline claims are in coding, where they report it as the strongest open-weights system they have measured, and in long-horizon agentic work. The weights are not public yet: Z.ai is holding them for a safety evaluation, saying capability in cybersecurity tasks grew faster than they expected during training.

What you will likely need to run it

Because Z.ai says the base is unchanged from GLM-5.2, the published GLM-5.2 footprint is the best available guide to what self-hosting GLM-5.3 will take. Treat this table as expectations, not measurements; we will replace it with measured numbers when the weights are out.

PropertyExpected (from the GLM-5.2 base)
ArchitectureMixture of experts, roughly 753B total parameters, roughly 40B active per token
Context256K tokens
LicenseGLM-5.2 shipped under MIT; we expect the same and will confirm at release
Hardware classA multi-GPU H200-class or B200-class shape. We will publish the exact shapes we qualify

What we will measure on day one

When the weights drop, we pin the release, review the license, and run our qualification process. This page then gets the same treatment as every model guide we publish:

How to be ready

If you want to run GLM-5.3 privately the week it lands, the only slow step you can do in advance is connecting your cloud account. Once the model reaches the catalog, deploying it is a few clicks: pick the shape, set a budget cap, confirm. Your prompts stay on your own instance.

Start a 24-hour trial