# 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. Version 2 improves on v1 in behavior and output quality.

- **Organisation:** summerAIO
- **Category:** Chat & Text Generation, Reasoning Models
- **Parameters:** 27.1B
- **Context length:** 262,144 tokens
- **Licence:** Apache 2.0 (Commercial use OK)
- **Released:** 2026-10-22
- **Hugging Face:** 1.5K downloads (30 days), 49 likes

## Estimated memory

| Quant | ≈ GB |
|---|---|
| Q2_K | 11.2 |
| Q3_K_M | 15.44 |
| Q4_K_M | 18.55 |
| Q5_K_M | 21.33 |
| Q6_K | 24.31 |
| Q8_0 | 30.63 |
| F16 | 55.45 |

## Runs with

- [Transformers](https://github.com/huggingface/transformers)

## About

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. Version 2 improves on v1 in behavior and output quality.

The model uses a custom architecture (qwen3_5_gdn24) with Gated DeltaNet linear-attention layers, shipped as remote code in this repository.

⚠️ trust_remote_code=True is required. Loading without it will fail or prompt for confirmation.

Built for book-scale inputs

Gated DeltaNet linear-attention layers

Refined over v1

## Alternatives

- [nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B-BF16](https://selfhost.directory/models/nvidia/nvidia-nemotron-3.5-lightning-30b-a3b-bf16) (31.6B (3B active), openmdw-1.1, ≈19.63 GB at Q4): NVIDIA Nemotron™ is a family of open models with open weights, training data, and recipes, delivering leading efficiency and accuracy for building specialized AI agents.
- [farbodtavakkoli/OTel-2.0-LLM-31B-IT](https://selfhost.directory/models/farbodtavakkoli/otel-2.0-llm-31b-it) (31.3B, Apache 2.0, ≈26.54 GB at Q4): Versioning notice: This card describes the current OTel 2.0 OSFT checkpoint. The model weights may be updated over time. For reproducible evaluation or production deployment, pin a specific model revision, checkpoint hash, or release tag rather than relying on the floating latest version.
- [ornith-ai/Ornith-1.0-35B](https://selfhost.directory/models/ornith-ai/ornith-1.0-35b) (35B (3.8B active), MIT, ≈21.87 GB at Q4): Aloha! 🌺 Today, we are releasing Ornith-1.0, a self-improving family of open-source models for agentic coding.
- [zai-org/GLM-4.7-Flash](https://selfhost.directory/models/zai-org/glm-4.7-flash) (31.2B (4.6B active), MIT, ≈26.35 GB at Q4): 👋 Join our Discord community. 📖 Check out the GLM-4.7 technical blog , technical report(GLM-4.5) . 📍 Use GLM-4.7-Flash API services on Z.ai API Platform. 👉 One click to GLM-4.7 .
- [poolside/Laguna-XS-2.1](https://selfhost.directory/models/poolside/laguna-xs-2.1) (33.4B (2.2B active), Custom licence, ≈21.58 GB at Q4): Laguna XS 2.1 is a 33B total parameter Mixture-of-Experts model with 3B activated parameters per token designed for agentic coding and long-horizon work on a local machine.
- [nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16](https://selfhost.directory/models/nvidia/nvidia-nemotron-3-nano-30b-a3b-bf16) (31.6B (3B active), nvidia-nemotron-open-model-license, ≈19.63 GB at Q4): Nemotron-3-Nano-30B-A3B-BF16 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response.

More: https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/alternatives

## Runs well on

- [Tesla P40](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/tesla-p40): Q5_K_M, est. 9.9 tok/s
- [Radeon RX 7900 XTX](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rx-7900-xtx): Q5_K_M, est. 27 tok/s
- [Instinct MI50 32GB](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/instinct-mi50): Q6_K, est. 25 tok/s
- [GeForce RTX 5090](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rtx-5090): Q6_K, est. 44 tok/s
- [Apple M4 Pro (48 GB)](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/apple-m4-pro-48gb): Q8_0, est. 5.2 tok/s
- [RTX A6000](https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2/on/rtx-a6000): Q8_0, est. 15 tok/s

## Similar size

- [openai/gpt-oss-20b](https://selfhost.directory/models/openai/gpt-oss-20b) (20.9B)
- [zai-org/GLM-4.7-Flash](https://selfhost.directory/models/zai-org/glm-4.7-flash) (31.2B)
- [Qwen/Qwen3-32B](https://selfhost.directory/models/qwen/qwen3-32b) (32.8B)
- [Qwen/Qwen3-30B-A3B](https://selfhost.directory/models/qwen/qwen3-30b-a3b) (30.5B)
- [LiquidAI/LFM2.5-24B-A2B](https://selfhost.directory/models/liquidai/lfm2.5-24b-a2b) (24B)
- [Qwen/Qwen2.5-32B-Instruct](https://selfhost.directory/models/qwen/qwen2.5-32b-instruct) (32.8B)

## FAQ

**How much VRAM does Qwen3.8-27B-Longbook27-v2 need?**
About 19 GB at Q4_K_M with an 8K context. Q8_0 needs about 31 GB and full precision about 55 GB. Longer contexts need more memory for the KV cache.

**Can Qwen3.8-27B-Longbook27-v2 run on the Tesla P40?**
Yes. It fits at Q5_K_M (about 21 GB), at an estimated 9.9 tokens/s. It fits comfortably on the Radeon RX 7900 XTX, Instinct MI50 32GB, RTX 5090.

**Can I use Qwen3.8-27B-Longbook27-v2 commercially?**
Yes. It is released under Apache 2.0. Permissive: use, modify and sell freely; keep the notice and licence text.

**What is the context length of Qwen3.8-27B-Longbook27-v2?**
262,144 tokens (256K). The full window needs far more memory than an 8K context.

**How do I run Qwen3.8-27B-Longbook27-v2 locally?**
It runs with Transformers. Each has copy-paste examples in its docs.

## Links

- huggingface: https://huggingface.co/summerAIO/Qwen3.8-27B-Longbook27-v2

---
Source: https://selfhost.directory/models/summeraio/qwen3.8-27b-longbook27-v2