Hcompany/Holo-3.1-9B

VISIONConcurrency Cost:1Model Size:9BQuant:FP8Ctx Length:32kTool Calling:SupportedPublished:May 29, 2026License:apache-2.0Architecture:Transformer0.0K Open Weights Cold

Holo-3.1-9B is a 9 billion parameter Vision-Language Model (VLM) developed by H Company, built upon the Qwen 3.5 family. Optimized for computer use agents, it extends automation capabilities across web, desktop, and mobile environments. This model features native function-calling support and enables local deployment through optimized quantized checkpoints, delivering strong performance for UI grounding and business workflows.

Loading preview...

Holo3.1: Vision-Language Models for Computer Use Agents

Holo3.1 is a family of Vision-Language Models (VLMs) developed by H Company, designed specifically for computer use agents. Building on the Holo3 series, this iteration expands its capabilities to include mobile environments, alongside existing support for browser and desktop automation. A key differentiator is its native function-calling support, which streamlines integration with various agent frameworks.

Key Capabilities & Features

  • Broad Automation: Supports automation across web, desktop, and mobile environments.
  • Native Function-Calling: Facilitates seamless integration with agent frameworks.
  • Local Deployment: Optimized quantized checkpoints enable efficient local deployment.
  • Performance: Delivers strong performance across computer use, UI grounding, mobile automation, and business workflows.
  • Model Family: Available in various sizes from 0.8B to 35B-A3B parameters, built on the Qwen 3.5 family.

Performance & Cost Efficiency

Holo3.1 models establish a strong Pareto frontier, balancing performance and inference cost across different model sizes. This makes them suitable for a range of applications, from lightweight local agents to more demanding enterprise deployments. The 9B parameter model offers a robust solution within this family for general computer use agent tasks.

Use Cases

  • Computer Use Agents: Automating tasks and interactions within digital environments.
  • UI Grounding: Understanding and interacting with user interfaces.
  • Mobile Automation: Controlling and automating tasks on mobile devices.
  • Enterprise Workflows: Streamlining business processes through intelligent automation.