Zenyx V3 is an efficient 1.5B-parameter Mixture-of-Experts (MoE) foundation model built for low-latency inference and high throughput. It is written from scratch in JAX/Flax and trained on TPU v5e-8. active per token, with a Sinkhorn transport-based gate. single shared key/value head, plus low-rank query and output projections. stability at scale. YaRN and RoPE scaling factors are precomputed so context can be extended at inference time beyond the trained length. All tasks are evaluated with the standard base-model protocol: the model scores the log-likelihood of every candidate continuation and the highest-scoring one is taken as the answer. Nothing is generated and no output parsing is…