LLMDB
Contribute
H Company logo

Holo3 35B-A3B

H CompanyOpen WeightsPending Human Review

Holo3 35B-A3B is H Company’s Apache-licensed sparse vision-language model for enterprise computer use. Based on Qwen3.5-35B-A3B, it is trained on open, synthetic, and human-annotated trajectories to improve perception, multi-step decisions, and navigation across web and desktop software. It was introduced on March 31 alongside a larger hosted Holo3 tier; the subsequent Hugging Face team article appeared April 1. This checkpoint provides downloadable weights and was originally served through the free API tier. Current API documentation instead lists Holo3.1 for the smaller tier, so continued first-party hosted inference on the original Holo3 35B is not asserted.

2026-03-31
35B language tier, 3B active
Qwen3.5 hybrid-attention Mixture-of-Experts vision-language Transformer
Apache-2.0
Compare with other models

Specifications

Parameters
35B language tier, 3B active
Architecture
Qwen3.5 hybrid-attention Mixture-of-Experts vision-language Transformer
License
Apache-2.0
Type
multimodal
Modalities
textimage

Benchmark Scores

Advanced Specifications

Model Family
Holo
Finetuned From
Qwen3.5-35B-A3B
API Access
Not Available
Chat Interface
Not Available

Capabilities & Limitations

Capabilities
computer usevisual groundingmulti-step navigationstructured 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 elementCurrent hosted availability of the original 35B tier is not independently verified
Notable Use Cases
local computer-use agentsenterprise workflow researchprivate GUI automation
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