---
title: Holo3-35B-A3B
canonical_url: "https://www.modelscope.cn/models/Hcompany/Holo3-35B-A3B"
md_url: "https://www.modelscope.cn/models/Hcompany/Holo3-35B-A3B.md"
repository: Hcompany/Holo3-35B-A3B
last_updated: 2026-04-02
license: apache-2.0
pipeline_tag: image-text-to-text
tasks:
  - image-text-to-text
model_type:
  - qwen3_5_moe
architectures:
  - Qwen3_5MoeForConditionalGeneration
base_model:
  - Qwen/Qwen3.5-35B-A3B
base_model_relation: finetune
parameters: 35.1B
tensor_type:
  - BF16
library_name:
  - safetensors
  - pytorch
frameworks:
  - pytorch
language:
  - en
downloads: 545253
stars: 40
tags:
  - multimodal
  - action
  - agent
  - pytorch
  - "computer use"
  - "gui agents"
  - moe
---

# Holo3-35B-A3B

> Holo3-35B-A3B - Hcompany 在 ModelScope 开源的模型。Holo3: Foundational Models for Navigation and Computer Use Agents

Hcompany/Holo3-35B-A3B 是 ModelScope 魔搭社区上的 35.1B 参数image-text-to-text模型，采用 apache-2.0 许可，基于 Qwen/Qwen3.5-35B-A3B 构建。

- **Repository**: Hcompany/Holo3-35B-A3B
- **License**: apache-2.0
- **Tasks**: image-text-to-text
- **Parameters**: 35.1B
- **Base model**: Qwen/Qwen3.5-35B-A3B
- **Tags**: multimodal, action, agent, pytorch, computer use, gui agents, moe
- **Downloads**: 545253
- **Stars**: 40
- **Last updated**: 2026-04-02

Source: https://www.modelscope.cn/models/Hcompany/Holo3-35B-A3B

---

# **Holo3: Foundational Models for Navigation and Computer Use Agents**


## **Model Description**

**Holo3** is our latest generation of large-scale Vision-Language Models (VLMs) specifically optimized for **GUI Agents**. Like its predecessors, it operates across diverse digital environments—web, desktop, and mobile—by interpreting visual interfaces, reasoning over complex content, and executing precise actions.

Holo3 achieves **state-of-the-art performance on OSWorld-Verified**, setting a new benchmark for computer use agents. While it retains the world-class web navigation capabilities of **Holo2**, the new **Holo3-35B-A3B** architecture is designed to thrive in realistic business environments.

* **Developed by:** [**H Company**](https://www.hcompany.ai/)
* **Model type:** Vision-Language Model for Navigation and Computer Use Agents
* **Architecture:** Sparse Mixture-of-Experts (MoE) with 35B total / 3B active parameters
* **Fine-tuned from model:** Qwen/Qwen3.5-35B-A3B
* **Blog Post:** [hcompany.ai/holo3](https://www.hcompany.ai/holo3)
* **Quickstart:** [hub.hcompany.ai/quickstart](https://hub.hcompany.ai/quickstart)
* **License:** Apache 2.0 License

---

<div align="center">

<p align="center"><img width=800 src="osworld_pareto_light.png"/></p>

</div>

---

## **Get Started**

Explore our [Quickstart guide](https://hub.hcompany.ai/quickstart) to learn how to integrate with our inference API.

---

## **Training Strategy**

**Holo3-35B-A3B** is based on the **Qwen3.5** architecture and has been reinforced to strengthen its core agentic pillars: perception and decision-making. The training pipeline utilizes a carefully curated mix of open-source datasets, large-scale synthetic trajectories, and high-quality human-annotated samples to ensure reliable multi-step reasoning.

---

## **Results**

### **State-of-the-Art Navigation (OSWorld-Verified)**
To benchmark **Holo3** on computer use and web navigation, we utilized the OSWorld and WebArena benchmarks. **Holo3-35B-A3B** achieves a **77.8%** score on OSWorld-Verified. Remarkably, it achieves this with only **3B active parameters**, providing SOTA performance at a fraction of the inference cost of leading proprietary models.

### **Enterprise Readiness (H Corporate Benchmark)**
To measure real-world utility, we developed the **H Corporate Benchmark**: a dedicated evaluation suite of 486 multi-step tasks across four categories: E-commerce, Business Software, Collaboration, and Multi-App workflows. Holo3 consistently outperforms significantly larger competitors in these dense, business-logic environments.

### **UI Localization & Grounding**
A world-class agent must see before it can act. Holo3 excels at localizing interaction elements and understanding their functions, as evidenced by top-tier performance on **ScreenSpot-Pro** and **OSWorld-G**.

<div align="center">

**Table 1: Evaluation results on computer use and grounding benchmarks.**

<p align="center"><img width=800 src="benchmark_table_light.png"/></p>

</div>

---

## **Citation**

```bibtex
@misc{hai2025holo3modelfamily,
      title={Holo3 - Open Foundation Models for Navigation and Computer Use Agents},
      author={H Company},
      year={2026},
      url={https://huggingface.co/Hcompany/Holo3-35B-A3B},
}
```