16:32
2026-09-24
dev.to
large-language-models
Running a Jev-Style Decision Model on One TPU v6e: What Fits, What It Costs, and What Changes From a GPU
A developer benchmarked a Jev-style decision read of Gemma 4 on a single Google Cloud TPU v6e chip with vLLM, finding that the E2B, E4B and 12B checkpoints fit at bf16 while the 26B-A4B fp8 build also…