---
title: tencent/Youtu-Parsing-Omni
url: https://recentmodel.com/models/tencent/Youtu-Parsing-Omni/
status: main board
published: 2026-10-09T06:42:18Z
updated: 2026-10-09T06:42:18Z
source: https://huggingface.co/tencent/Youtu-Parsing-Omni
---

# tencent/Youtu-Parsing-Omni

Youtu-Parsing-Omni is a compact (5B) omni-modal parsing model. Dense, 5.3B params. Context: 1M tokens (config). License: youtu-parsing.


- **Org:** tencent
- **Released:** 2026-10-09
- **Status:** main board
- **License:** youtu-parsing (restricted)
- **Parameters:** 5.3B
- **Architecture:** dense · YoutuVITAForCausalLM
- **Context:** 1,048,576 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 116 HF likes · 2584 downloads

## Runs on

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

- Q4 ~4.6 GB (estimated): 8GB GPU (4060 / 3070)
- Q8 ~7.1 GB (estimated): 12GB GPU (RTX 3060), Mac 16GB
- FP16 ~12.1 GB: 16GB GPU (5060 Ti / 4060 Ti / 4080 / 5080), 24GB GPU (3090 / 4090), 32GB GPU (5090), 48GB GPU (RTX 6000 Ada / A6000), 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), 16GB GPU (7800 XT / 9070 XT), 24GB GPU (7900 XTX), Strix Halo 128GB unified (~96GB usable), Arc B60 24GB, Arc B70 32GB, Mac 24GB, Mac 36GB, Mac 48GB, Mac 64GB (M1 Max), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 32GB RAM (slow), CPU only, 64GB RAM (slow), CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/tencent/Youtu-Parsing-Omni)