---
title: summerAIO/Qwen3.8-27B-Longbook27-v2
url: https://recentmodel.com/models/summerAIO/Qwen3.8-27B-Longbook27-v2/
status: just landed · new, unvetted
published: 2026-10-22T16:31:34Z
updated: 2026-11-02T00:25:15Z
source: https://huggingface.co/summerAIO/Qwen3.8-27B-Longbook27-v2
---

# summerAIO/Qwen3.8-27B-Longbook27-v2

Qwen3.8-27B-Longbook27-v2 is a fine-tuned 27B model for understanding and generating long-form text such as books, papers, and lengthy reports. Dense, 27B params. Context: 256K tokens (config). License: apache-2.0.


- **Org:** summerAIO
- **Released:** 2026-10-22
- **Status:** just landed · new, unvetted
- **License:** apache-2.0 (permissive)
- **Parameters:** 27.1B
- **Architecture:** dense · Qwen35GDN24ForCausalLM
- **Context:** 262,144 tokens
- **Task:** text-generation · text
- **Signal:** 24 HF likes · 139 downloads

## Runs on

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

- Q4 ~19.3 GB (estimated): 24GB GPU (3090 / 4090), 32GB GPU (5090), 24GB GPU (7900 XTX), Mac 36GB, CPU only, 32GB RAM (slow)
- Q8 ~31.9 GB (estimated): 48GB GPU (RTX 6000 Ada / A6000), Mac 48GB, Mac 64GB (M1 Max), CPU only, 64GB RAM (slow)
- FP16 ~57.2 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/summerAIO/Qwen3.8-27B-Longbook27-v2)
- [Ollama](https://ollama.com/library/qwen3.8)