Skip to content
AI 인텔리전스Sep 18, 2026AI 인텔리전스
기사

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.

AI 생성: 요약은 링크된 출처를 바탕으로 AI가 작성했습니다. AI 활용 방식

AI 생성출처: Pandaily
01

출처 브리프

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.