---
title: inclusionAI/ZwZ2-27B
url: https://recentmodel.com/models/inclusionAI/ZwZ2-27B/
status: just landed
published: 2026-10-16T05:42:32Z
updated: 2026-10-27T23:20:03Z
source: https://huggingface.co/inclusionAI/ZwZ2-27B
---

# inclusionAI/ZwZ2-27B

ZwZ2-27B is the Qwen3.6-27B-based model in Zooming-without-Zooming-v2 (ZwZ2). Dense, 27B params. Context: 256K tokens (config).


- **Org:** inclusionAI
- **Released:** 2026-10-16
- **Status:** just landed
- **License:** unknown
- **Parameters:** 27.4B
- **Architecture:** dense · Qwen3_5ForConditionalGeneration
- **Context:** 262,144 tokens
- **Task:** image-text-to-text · vision
- **Signal:** 5 HF likes · 7 downloads

## Runs on

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

- Q4 ~19.5 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~32.2 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.8 GB: 96GB GPU (RTX Pro 6000 Blackwell), 1× DGX Spark (128GB), 2× DGX Spark (256GB), Strix Halo 128GB unified (~96GB usable), Mac 96GB, Mac 128GB, Mac 192GB, Mac 256GB, Mac 512GB, CPU only, 128GB RAM (slow), CPU only, 256GB RAM (slow)

## Links

- [Hugging Face](https://huggingface.co/inclusionAI/ZwZ2-27B)