---
title: ReaderLM-v2-GGUF
canonical_url: "https://www.modelscope.cn/models/manateelazycat/ReaderLM-v2-GGUF"
md_url: "https://www.modelscope.cn/models/manateelazycat/ReaderLM-v2-GGUF.md"
repository: manateelazycat/ReaderLM-v2-GGUF
last_updated: 2026-10-23
license: cc-by-nc-4.0
pipeline_tag: text-generation
tasks:
  - text-generation
base_model:
  - jinaai/ReaderLM-v2
base_model_relation: quantized
library_name:
  - gguf
language:
  - en
  - zh
downloads: 6
stars: 0
tags:
  - gguf
  - llama-cpp
  - readerlm
  - jetson
  - qwen2
---

# ReaderLM-v2-GGUF

> ReaderLM-v2-GGUF - manateelazycat 在 ModelScope 开源的模型。ReaderLM-v2 Q4KM for Jetson

manateelazycat/ReaderLM-v2-GGUF 是 ModelScope 魔搭社区上的text-generation模型，采用 cc-by-nc-4.0 许可，基于 jinaai/ReaderLM-v2 构建。

- **Repository**: manateelazycat/ReaderLM-v2-GGUF
- **License**: cc-by-nc-4.0
- **Tasks**: text-generation
- **Base model**: jinaai/ReaderLM-v2
- **Tags**: gguf, llama-cpp, readerlm, jetson, qwen2
- **Downloads**: 6
- **Stars**: 0
- **Last updated**: 2026-10-23

Source: https://www.modelscope.cn/models/manateelazycat/ReaderLM-v2-GGUF

---

# ReaderLM-v2 Q4_K_M for Jetson

This repository mirrors the tested GGUF Q4_K_M conversion by mradermacher, from https://huggingface.co/mradermacher/ReaderLM-v2-GGUF at revision 08a86568ae97ff37fbc22688ac919be29f5bca3e. Original model: Jina AI ReaderLM-v2. No weight bytes were changed.

The file SHA-256 is d5bf01392bc58fc49f15d9441b16969da388c6601b9c192d4a6a1d8f31be2512.

Tested on AGX Orin JetPack 6.2 with pinned llama.cpp 970b51ce7c9ba5fff0726c5e9994f1c2f0e4eedc: Q4_K_M weights, f16 KV, Flash Attention, CUDA Graph, 32K total input/output capacity, one slot, --cache-ram 0. A synthetic short HTML extraction decoded about 81 tokens/s. This is a warm workload measurement, not an accuracy guarantee or full-page throughput limit.

ReaderLM is specialized for HTML-to-Markdown and schema-guided JSON extraction. It is not a general-purpose chat recommendation. The deployed 32K limit is smaller than the upstream model maximum.

## License / 许可证

CC-BY-NC-4.0. Preserve Jina AI attribution and the original license. 非商业许可；商业使用请向 Jina AI 获取授权。See NOTICE.md.