--- title: Holo3-35B-A3B-FP8 canonical_url: "https://www.modelscope.cn/models/prithivMLmods/Holo3-35B-A3B-FP8" md_url: "https://www.modelscope.cn/models/prithivMLmods/Holo3-35B-A3B-FP8.md" repository: prithivMLmods/Holo3-35B-A3B-FP8 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: - Hcompany/Holo3-35B-A3B base_model_relation: quantized parameters: 35.1B tensor_type: - F32 - F8_E4M3 library_name: - safetensors - pytorch frameworks: - pytorch language: - en downloads: 668223 stars: 0 tags: - multimodal - action - agent - pytorch - "computer use" - "gui agents" - moe --- # Holo3-35B-A3B-FP8 > Holo3-35B-A3B-FP8 - prithivMLmods 在 ModelScope 开源的模型。Holo3-35B-A3B-FP8 is an FP8-compressed evolution of Holo3-35B-A3B. This variant leverages F32 · F8E4M3 precision formats to significantly reduce memory footprint and improve inference efficiency while… prithivMLmods/Holo3-35B-A3B-FP8 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 Hcompany/Holo3-35B-A3B 构建。 - **Repository**: prithivMLmods/Holo3-35B-A3B-FP8 - **License**: apache-2.0 - **Tasks**: image-text-to-text - **Parameters**: 35.1B - **Base model**: Hcompany/Holo3-35B-A3B - **Tags**: multimodal, action, agent, pytorch, computer use, gui agents, moe - **Downloads**: 668223 - **Stars**: 0 - **Last updated**: 2026-04-02 Source: https://www.modelscope.cn/models/prithivMLmods/Holo3-35B-A3B-FP8 --- # **Holo3-35B-A3B-FP8** > Holo3-35B-A3B-FP8 is an FP8-compressed evolution of Holo3-35B-A3B. This variant leverages F32 · F8_E4M3 precision formats to significantly reduce memory footprint and improve inference efficiency while maintaining strong output quality. [Holo3-35B-A3B](https://huggingface.co/Hcompany/Holo3-35B-A3B) from H Company is a state-of-the-art sparse Mixture-of-Experts (MoE) vision-language model with 35B total parameters but only 3B active per inference, fine-tuned from Qwen3.5-35B-A3B for GUI navigation and computer-use agents operating across web, desktop, and mobile environments. Achieving SOTA 77.8% on the OSWorld-Verified benchmark — surpassing proprietary models at dramatically lower cost and latency — it excels at interpreting visual interfaces, reasoning over complex content, and executing precise actions such as form filling, spreadsheet editing, and browser control for enterprise automation. It is Apache 2.0-licensed with open weights available on Hugging Face. ## **Recipe** ```yaml default_stage: default_modifiers: QuantizationModifier: targets: [Linear] ignore: ['re:.*lm_head', 're:visual.*', 're:model.visual.*', 're:.*mlp.gate$', 're:.*embed_tokens$', 're:.*shared_expert_gate$', 're:.*linear_attn.*'] scheme: FP8_DYNAMIC bypass_divisibility_checks: false ``` --- # **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 ---

--- ## **Get Started** Explore our [Quickstart guide](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**.
**Table 1: Evaluation results on computer use and grounding benchmarks.**

--- ## **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}, } ```