Z.AI / 2026
GLM-5.2
An open flagship designed for long engineering trajectories across a sourced million-token context.
DECISION BRIEF
Long-horizon coding
The exact BF16 artifact is 1.51 TB. Active parameters remain unknown in registry v1 because the reviewed primary sources do not establish the value.
Publicly available checkpoints; verify terms before commercial deployment.
Unknown remains explicit until the exact checkpoint license is verified and sourced.
Architecture values are linked to the publishing organization.
ARCHITECTURE
Compute is sparse. Residency is not.
The exact BF16 artifact is 1.51 TB. Active parameters remain unknown in registry v1 because the reviewed primary sources do not establish the value.
Expert topology: 256 / top-8. The active-parameter count approximates token-level compute; it does not determine checkpoint memory, KV-cache demand, expert placement, or interconnect pressure.
GLM-5.2 release
zai-org/GLM-5.2@b4734de4facf · 1.51 TB
NEXT ACTION
Test the workload, not the headline.
Start with checkpoint residency, then layer in context, concurrency, runtime overhead, topology, and resilience.
Build an assurance plan