---
title: CapRL-Qwen3VL-4B-GGUF
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/CapRL-Qwen3VL-4B-GGUF"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/CapRL-Qwen3VL-4B-GGUF.md"
repository: Shanghai_AI_Laboratory/CapRL-Qwen3VL-4B-GGUF
last_updated: 2025-12-29
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
base_model:
  - internlm/CapRL-Qwen3VL-4B
base_model_relation: quantized
library_name:
  - gguf
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 399
stars: 0
tags:
  - multimodal
  - "image caption"
  - captioning
  - gguf
---

# CapRL-Qwen3VL-4B-GGUF

> CapRL-Qwen3VL-4B-GGUF - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。static quants of https://huggingface.co/internlm/CapRL-Qwen3VL-4B

Shanghai_AI_Laboratory/CapRL-Qwen3VL-4B-GGUF 是 ModelScope 魔搭社区上的image-text-to-text模型，采用 apache-2.0 许可，基于 internlm/CapRL-Qwen3VL-4B 构建。

- **Repository**: Shanghai_AI_Laboratory/CapRL-Qwen3VL-4B-GGUF
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Base model**: internlm/CapRL-Qwen3VL-4B
- **Tags**: multimodal, image caption, captioning, gguf
- **Downloads**: 399
- **Stars**: 0
- **Last updated**: 2025-12-29

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/CapRL-Qwen3VL-4B-GGUF

---

## About

static quants of https://huggingface.co/internlm/CapRL-Qwen3VL-4B

weighted/imatrix quants are available at https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF

## Usage

If you are unsure how to use GGUF files, refer to one of [TheBloke's
READMEs](https://huggingface.co/TheBloke/KafkaLM-70B-German-V0.1-GGUF) for
more details, including on how to concatenate multi-part files.

## Provided Quants

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

| Link | Type | Size/GB | Notes |
|:-----|:-----|--------:|:------|
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-mmproj-Q8_0.gguf) | mmproj-Q8_0 | 0.6 | multi-modal supplement |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-mmproj-f16.gguf) | mmproj-f16 | 0.9 | multi-modal supplement |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-Q2_K.gguf) | Q2_K | 1.8 |  |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-Q4_K_S.gguf) | Q4_K_S | 2.6 | fast, recommended |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-Q4_K_M.gguf) | Q4_K_M | 2.7 | fast, recommended |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-Q6_K.gguf) | Q6_K | 3.6 | very good quality |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-Q8_0.gguf) | Q8_0 | 4.7 | fast, best quality |
| [GGUF](https://huggingface.co/internlm/CapRL-Qwen3VL-4B-GGUF/resolve/main/CapRL-Qwen3VL-4B-f16.gguf) | f16 | 8.8 | 16 bpw, overkill |

## Citation

If you find this project useful, please cite:

```bibtex
@article{xing2025caprl,
  title={{CapRL}: Stimulating Dense Image Caption Capabilities via Reinforcement Learning},
  author={Xing, Long and Dong, Xiaoyi and Zang, Yuhang and Cao, Yuhang and Liang, Jianze and Huang, Qidong and Wang, Jiaqi and Wu, Feng and Lin, Dahua},
  journal={arXiv preprint arXiv:2509.22647},
  year={2025}
}
```