Holo1
Holo1 is H Company’s original open-weight action vision-language family, with 3B and 7B language-model tiers derived from Qwen2.5-VL. It is trained for web-interface understanding, precise element localization, navigation policy generation, and validating agent progress. The June 3 release includes public weights and a technical paper, earlier than a later provider retrospective’s June 25 date. Holo1 can serve different roles inside the modular Surfer-H harness; the model identity is distinct from that application. Licensing differs by size: the 7B checkpoint uses Apache 2.0, while the 3B repository includes H Product Research terms incorporating the Qwen research license.
2025-06-03
3B and 7B language tiers
Qwen2.5-VL dense vision-language Transformers
Size-specific: H Product Research License (3B); Apache-2.0 (7B)
Specifications
- Parameters
- 3B and 7B language tiers
- Architecture
- Qwen2.5-VL dense vision-language Transformers
- License
- Size-specific: H Product Research License (3B); Apache-2.0 (7B)
- Type
- multimodal
- Modalities
- textimage
Benchmark Scores
Advanced Specifications
- Model Family
- Holo
- Finetuned From
- Qwen2.5-VL Instruct family
- API Access
- Not Available
- Chat Interface
- Not Available
- Variants
- Holo1-3BHolo1-7B
Capabilities & Limitations
- Capabilities
- web navigationUI localizationvisual understandingaction generation
- Known Limitations
- Actions require an external computer-use harnessPerformance depends on software environments and evaluation settingsGenerated actions can fail or affect the wrong interface elementResearch terms apply to 3B; the family is not uniformly Apache-licensed
- Notable Use Cases
- browser automationvisual web extractioncomputer-use research
- Tool Use Support
- Yes