Z.ai used GLM-5.3 agents to stand up inference on 100,000+ Chinese accelerators in under two weeks and tripled throughput.

Z.ai documented going from initial model adaptation to production for GLM-5.3-Flash in under two weeks, with GLM-5.3-powered agents doing most of the porting work. Intra-node tensor parallelism for linear attention and the LM head, ReplaySSM, W8A8 quantization, mixed INT8/FP8/BF16 cache quantization, Layer Split, and an Encode-Prefill-Decode disaggregated architecture gave about 3x end-to-end throughput at per-token costs they describe as comparable to mainstream NVIDIA GPUs. Launched anonymously as "Ox-Alpha" on OpenCode and OpenRouter, it became the most-used model on both, processing over 62 trillion tokens in six days. Vendor-reported cost parity, but the 62-trillion-token usage number is externally visible.