---
title: ibyteohdear/10Eros-Max-Transformer_8stepTURBO_beta7
url: https://recentmodel.com/models/ibyteohdear/10Eros-Max-Transformer_8stepTURBO_beta7/
status: just landed · new, unvetted
published: 2026-10-28T05:21:08Z
updated: 2026-11-01T12:18:40Z
source: https://huggingface.co/ibyteohdear/10Eros-Max-Transformer_8stepTURBO_beta7
---

# ibyteohdear/10Eros-Max-Transformer_8stepTURBO_beta7

Image to video model from ibyteohdear (HF pipeline tag; the card has no one-line description). Dense, 20B params.


- **Org:** ibyteohdear
- **Released:** 2026-10-28
- **Status:** just landed · new, unvetted
- **License:** unknown
- **Parameters:** 20.1B
- **Architecture:** dense
- **Task:** image-to-video · video
- **Signal:** 2 HF likes · 65 downloads

## Runs on

estimate from params; sizing calculation, not tested.

- Q4 ~14.8 GB (estimated): 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 24GB GPU (3090 / 4090), 16GB GPU (7800 XT / 9070 XT), 24GB GPU (7900 XTX), Mac 24GB
- Q8 ~24.1 GB (estimated): 32GB GPU (5090), Arc B70 32GB, Mac 36GB, Mac 48GB, CPU only, 32GB RAM (slow)
- FP16 ~42.9 GB (estimated): 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 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/ibyteohdear/10Eros-Max-Transformer_8stepTURBO_beta7)