Zhipu AI (Z.ai) models
The GLM line - MIT-licensed, from Flash to frontier.
Run on your device
GLM-5.2
Zhipu AI · Jun 2026Zhipu's GLM-5.2 - a 753B mixture-of-experts with a 1M-token context. For very large workstations: a big graphics card and 384 GB or more of main memory, experts in main memory.
from 253.9 GBruns from 384 GB RAM1M contextMIT
GLM-4.7 Flash
Zhipu (Z.ai) · Jan 2026Zhipu's fast GLM model — a strong all-rounder tuned for agentic coding, reasoning, and tool use. The lighter "Flash" tier of the GLM family; the 30B MoE runs only 3B parameters per token.
from 18.3 GBruns from 32 GB RAM198K contextMIT