Zhipu Reveals Ox Alpha as GLM-5.3-Flash, Serving 100T Tokens/Day on Chinese GPUs
pstAsiatech · x · 2026-08-27
Zhipu AI has unmasked the mystery "Ox Alpha" model as GLM-5.3-Flash. The company revealed that the model runs entirely on domestic Chinese GPU hardware and currently processes 100 trillion tokens per day. This throughput figure is particularly striking given four years of chip export controls, highlighting the massive inference capabilities of China's local compute infrastructure.
More from Infra
- Copper to optical: optical backplanes seen as necessary as racks move to optics — BenBajarin · 2026-10-16
- Polymarket prices 28% odds a US state enacts data center moratorium by year-end — Polymarket · 2026-10-16
- Pennsylvania residents reject $10,000-per-household offer for massive Amazon data center — Polymarket · 2026-10-16
- PyTorch now runs natively on AWS Trainium with zero code changes — PyTorch · 2026-10-16
- Chinese labs run on ~1/10 US compute; ByteDance pays 2-4x to hoover up SEA supply — robleclerc · 2026-10-16
- Zymtrace raises $12.2M and hires ML engineers to build agents that fix GPU bottlenecks — cfregly · 2026-10-16