GLM-5.3-Flash: 320B Open-Weight Model With 18B Active and 1M-Token Context

Z.ai released the open multimodal MoE model GLM-5.3-Flash under the MIT license on August 26, 2026: 320 billion parameters with 18 billion active per token and context up to 1 million tokens. The model scored 57 in the Artificial Analysis index at about $0.045 per task and was served on Chinese AI chips.

• 320B total parameters, 18B active per token, MIT license
• Context of 1M input tokens and up to 128K output tokens
• AutomationBench rose from 26.2% to 48.8% over one generation
• Served on Chinese chips, not Nvidia