Cloud TPU v6e-1 ( ct6e-standard-1t , one v6e chip, 32 GB HBM), GCE flex-start, europe-west4-a. vLLM baseline measured 2026-07-21. The workload nobody benchmarks Serving benchmarks optimize for the wrong shape.
Source: [Dev.to](https://dev.to/xbill/one-tpu-chip-eight-agents-serving-small-agent-workloads-with-raw-jax-2cc4)