---
title: Alibaba-DAMO-Academy/RynnUnify-Base
url: https://recentmodel.com/models/Alibaba-DAMO-Academy/RynnUnify-Base/
status: just landed · new, unvetted
published: 2026-10-22T03:28:08Z
updated: 2026-10-26T11:26:59Z
source: https://huggingface.co/Alibaba-DAMO-Academy/RynnUnify-Base
---

# Alibaba-DAMO-Academy/RynnUnify-Base

RynnUnify is a Mixture-of-Transformers architecture with an autoregressive Reasoner and a rectified-flow video Generator. 16B params. License: apache-2.0.


- **Org:** Alibaba-DAMO-Academy
- **Released:** 2026-10-22
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 15.7B
- **Architecture:** Cosmos3OmniModel
- **Task:** any-to-any · omni
- **Signal:** 3 HF likes · 42 downloads

## Runs on

mixed: real files + estimate; sizing calculation, not tested.

- Q4 ~11.7 GB (estimated): 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 16GB GPU (7800 XT / 9070 XT), Mac 16GB, Mac 24GB
- Q8 ~19.0 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Arc B60 24GB, Arc B70 32GB, Mac 36GB, CPU only, 32GB RAM (slow)
- FP16 ~33.8 GB: 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/Alibaba-DAMO-Academy/RynnUnify-Base)