Model Detail
ZAYA1-74B-preview
—ZAYA1-74B-preview is an AI model with 74B parameters released by Zyphra. Distributed under the permissive apache-2.0 license.
ZAYA1-74B-preview ships with 74B parameters. Total weight footprint is approximately 74.8 GB, which is the relevant figure when planning local-inference VRAM. The apache-2.0 license is permissive, allowing commercial deployment and derivative work without per-seat fees, though attribution requirements still apply.
ZAYA1-74B-preview is best fit for general-purpose AI workloads. Treat this as a starting matrix rather than a benchmark verdict — the right deployment usually depends on the specific evaluation suite that mirrors your workload.
ZAYA1-VL-8B Technical Report
arXiv:2605.08560v1 Announce Type: cross Abstract: We present ZAYA1-VL-8B, a compact mixture-of-experts vision-language model built upon our in-house language model, ZAYA1-8B. Despite its compact size, ZAYA1-VL achieves performance competitive with leading base models such as Molmo2-4B and InternVL3.
ZAYA1-8B Technical Report
arXiv:2605.05365v1 Announce Type: new Abstract: We present ZAYA1-8B, a reasoning-focused mixture-of-experts (MoE) model with 700M active and 8B total parameters, built on Zyphra's MoE++ architecture. ZAYA1-8B's core pretraining, midtraining, and supervised fine-tuning (SFT) were performed on a full-
