hayulalab/hidden-tiger-paper

Run inference — Hayula Research

Hayula AI Lab

Abstract

DeepSeek V3 and R1 represent the frontier of Mixture-of-Experts language models at 671 billion total parameters (37B active per token). Current hardware limitations restrict deployment to multi-GPU clusters: no single H100 (80GB), A100 (80GB), or consumer GPU can load the model at any practical quantization level. We demonstrate that the Apple M2 Ultra with 192GB unified memory is the only consumer-grade hardware capable of running this architecture, at IQ1_M quantization (139GB) fitting entirel

Files

File	Description
paper.md	Full paper (Markdown)
README.md	This model card

Citation

@techreport{hayulalab2026hiddentiger,
    title={Run inference — Hayula Research},
    author={Hayula AI Lab},
    year={2026},
    url={https://huggingface.co/hayulalab/hidden-tiger-paper}
}

---

hayulalab — Open Source AI Research