LLMDB
Contribute
H Company logo

Holo2 4B/8B

H CompanyOpen WeightsPending Human Review

The 4B and 8B Holo2 tiers are H Company’s compact, Apache-licensed vision-language models for computer use across web, desktop, and mobile environments. Derived from Qwen3-VL Thinking checkpoints, they combine interface grounding with navigation and self-generated reasoning, improving on earlier Holo localizers that relied on an external navigation model. Training uses curated localization and agent datasets, and the models can operate in a ReAct-style external harness such as Surfer 2. The two dense sizes are grouped here; the larger sparse Holo2 tiers have different licensing and separate records. Public weights support private deployment with compatible inference frameworks.

2025-11-13
4B and 8B language tiers
Qwen3-VL dense vision-language Transformers
Apache-2.0
Compare with other models

Specifications

Parameters
4B and 8B language tiers
Architecture
Qwen3-VL dense vision-language Transformers
License
Apache-2.0
Type
multimodal
Modalities
textimage

Benchmark Scores

Advanced Specifications

Model Family
Holo
Finetuned From
Qwen3-VL Thinking family
API Access
Not Available
Chat Interface
Not Available
Variants
Holo2-4BHolo2-8B

Capabilities & Limitations

Capabilities
computer useUI groundingreasoningaction 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 element
Notable Use Cases
local computer assistantscross-platform automationagent research
Tool Use Support
Yes

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