Z.ai releases GLM-5.3-Flash
Z.ai released GLM-5.3-Flash, a 320B-parameter model with 18B active parameters, native vision for working with interfaces and browsers, and support for office and research workflows. Open weights are on Hugging Face.
Source
"Combines linear and sparse attention with 320B total parameters and 18B activated, significantly reducing compute and KV-cache requirements."
Published