LLMDB
Contribute
H Company logo

Holo3 122B-A10B

H CompanyProprietaryPending Human Review

Holo3 122B-A10B is H Company’s larger hosted computer-use model, positioned for longer and more complex enterprise workflows. Its mixture-of-experts architecture has 122B total language parameters with about 10B active per token, and combines screenshot understanding with multi-step navigation and structured actions. It was publicly introduced March 31, before the April 1 Hugging Face article. The current provider catalog documents a 65,536-token context, paid API access, and research-only non-commercial weight terms. An openly downloadable 122B checkpoint was not verified, so public access is recorded through the API rather than extrapolated from the Apache-licensed 35B tier.

2026-03-31
122B language tier, 10B active
Mixture-of-Experts vision-language model
Research only (non-commercial)
Compare with other models

Specifications

Parameters
122B language tier, 10B active
Architecture
Mixture-of-Experts vision-language model
License
Research only (non-commercial)
Context Window
65,536 tokens
Type
multimodal
Modalities
textimage

Benchmark Scores

Advanced Specifications

Model Family
Holo
API Access
Available
Chat Interface
Not Available

Capabilities & Limitations

Capabilities
computer usemulti-step navigationvisual reasoningstructured actions
Known Limitations
Actions require an external computer-use harnessPerformance depends on software environments and evaluation settingsGenerated actions can fail or affect the wrong interface elementPublicly downloadable 122B weights are not verifiedResearch-only licensing differs from the smaller Apache tier
Notable Use Cases
enterprise GUI workflowscomplex software automationhosted computer-use agents
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