LLMDB
Contribute
H Company logo

Holo1.5

H CompanyOpen WeightsPending Human Review

Holo1.5 is H Company’s improved Qwen2.5-VL-based family for interface grounding, UI understanding, and screen question answering, spanning 3B, 7B, and 72B language tiers. It specializes in identifying requested interface elements across browser, desktop, and mobile screens, and can be combined with external navigation models. The provider’s Holo2 announcement explicitly dates its release to September 25, preceding the currently displayed October 9 announcement page. Weights are public, but licenses vary: H Product Research terms for 3B, Apache 2.0 for 7B, and CC-BY-NC-4.0 for 72B. This page groups routine sizes while preserving their different usage terms.

2025-09-25
3B, 7B, and 72B language tiers
Qwen2.5-VL dense vision-language Transformers
Size-specific: H Product Research License (3B); Apache-2.0 (7B); CC-BY-NC-4.0 (72B)
Compare with other models

Specifications

Parameters
3B, 7B, and 72B language tiers
Architecture
Qwen2.5-VL dense vision-language Transformers
License
Size-specific: H Product Research License (3B); Apache-2.0 (7B); CC-BY-NC-4.0 (72B)
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
Holo1.5-3BHolo1.5-7BHolo1.5-72B

Capabilities & Limitations

Capabilities
UI localizationscreen question answeringcross-platform visual grounding
Known Limitations
Specialized grounding performance does not establish end-to-end agent successLicenses differ by checkpoint sizeCurrent first-party hosted availability is not verified
Notable Use Cases
computer-use perceptionUI understanding researchscreen-grounded assistants

Resources

Related Models

Holo4 27B

H Company

Holo4 27B

Holo4 27B is H Company’s computer-use vision-language model built on Qwen3.8-27B. It is post-trained to work across graphical interfaces, code, MCP tools, and APIs, using screenshots and tool results to choose its next actions. Released weights support local agent research; an external harness executes clicks, typing, and code and returns observations. The dense 27B model uses a non-commercial weight license, unlike the Apache-licensed sparse Holo4 tier. Its card specifies a 262,144-token configuration limit; this is not a promise of consistent task performance throughout that window.

Typemultimodal
Parameters27B
2026-09-28
Open Weights
DetailsCompare

Holo4 35B-A3B

H Company

Holo4 35B-A3B

Holo4 35B-A3B is H Company’s computer-use vision-language model built on Qwen3.6-35B-A3B. It is post-trained to work across graphical interfaces, code, MCP tools, and APIs, using screenshots and tool results to choose its next actions. Released weights support local agent research; an external harness executes clicks, typing, and code and returns observations. The sparse model activates about 3B language parameters per token but still needs memory for its full checkpoint. Its card specifies a 262,144-token context. Apache-licensed weights and hosted H Models API access are available.

Typemultimodal
Parameters35B total, 3B active
2026-09-28
Open Weights
DetailsCompare

Holotron4 Nano

H Company

Holotron4 Nano

Holotron4 Nano is H Company’s computer-use vision-language model built on NVIDIA Nemotron 3 Nano Omni. It is post-trained to work across graphical interfaces, code, MCP tools, and APIs, using screenshots and tool results to choose its next actions. Released weights support local agent research; an external harness executes clicks, typing, and code and returns observations. The sparse model activates about 3B language parameters per token but still needs memory for its full checkpoint. Its card specifies a 262,144-token context. The NVIDIA Open Model Agreement governs its weights; the released page establishes text and image understanding without assuming every modality of its Omni backbone.

Typemultimodal
Parameters30B language tier, 3B active
2026-09-28
Open Weights
DetailsCompare