---
license: other
language:
- en
base_model:
- prithivMLmods/Herculis-CUA-GUI-Actioner-4B
pipeline_tag: image-text-to-text
library_name: transformers
tags:
- text-generation-inference
- agent
- llama.cpp
- computer-use-agent
- gui-actioning
- ui-localization
- multimodal-agent
- screen-understanding
- task-automation
- desktop-agent
- ui-vqa
---

# **Herculis-CUA-GUI-Actioner-4B-GGUF**

> Herculis-CUA-GUI-Actioner-4B is a Computer Use Agent (CUA) multimodal model designed for GUI understanding, UI localization, and action execution across web, desktop, and mobile environments. It focuses on visual grounding, intent driven actioning, and UI based question answering (VQA), enabling reliable interaction with real world software interfaces. The model is optimized for efficient inference while maintaining strong accuracy on complex UI workflows.


## Quick Start with llama.cpp 

> Link: https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF?library=llama-cpp-python 

## Herculis-CUA-GUI-Actioner-4B [GGUF]

| File Name | Quant Type | File Size | File Link |
| - | - | - | - |
| Herculis-CUA-GUI-Actioner-4B.BF16.gguf | BF16 | 6.18 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.BF16.gguf) |
| Herculis-CUA-GUI-Actioner-4B.F16.gguf | F16 | 6.18 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.F16.gguf) |
| Herculis-CUA-GUI-Actioner-4B.F32.gguf | F32 | 12.3 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.F32.gguf) |
| Herculis-CUA-GUI-Actioner-4B.Q8_0.gguf | Q8_0 | 3.29 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.Q8_0.gguf) |
| Herculis-CUA-GUI-Actioner-4B.mmproj-bf16.gguf | mmproj-bf16 | 1.34 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.mmproj-bf16.gguf) |
| Herculis-CUA-GUI-Actioner-4B.mmproj-f16.gguf | mmproj-f16 | 1.34 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.mmproj-f16.gguf) |
| Herculis-CUA-GUI-Actioner-4B.mmproj-f32.gguf | mmproj-f32 | 2.67 GB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.mmproj-f32.gguf) |
| Herculis-CUA-GUI-Actioner-4B.mmproj-q8_0.gguf | mmproj-q8_0 | 848 MB | [Download](https://huggingface.co/prithivMLmods/Herculis-CUA-GUI-Actioner-4B-GGUF/blob/main/Herculis-CUA-GUI-Actioner-4B.mmproj-q8_0.gguf) |

## Quants Usage 

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

Here is a handy graph by ikawrakow comparing some lower-quality quant
types (lower is better):

![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)