Skip to content
Inteligencia IASep 18, 2026Inteligencia IA
Artigo

Zhipu AI launched GLM-5.3-FlashX, claiming nearly 200 tokens per second inference on ~100,000 domestic accelerators.

The base Flash model is a 320B MoE with 18B active parameters, optimized by an Infra Agent serving stack.

Gerado por IA: resumos escritos por IA a partir das fontes indicadas. Como usamos a IA

Gerado por IAFonte: Pandaily
01

Brief da fonte

Zhipu AI launched GLM-5.3-FlashX, claiming nearly 200 tokens per second inference on ~100,000 domestic accelerators. The base Flash model is a 320B MoE with 18B active parameters, optimized by an Infra Agent serving stack.