LLMDB
Contribute
H Company logo

Holo3.1

H CompanyOpen WeightsPending Human Review

Holo3.1 is H Company’s updated computer-use model family, adding mobile robustness, native function-calling protocols, and practical local deployment. It spans dense 0.8B, 4B, and 9B Qwen3.5-derived tiers plus a sparse 35B-A3B tier whose current card identifies Qwen3.6 ancestry. The release includes Apache-licensed weights and optimized FP8, NVFP4, and Q4 GGUF options for the larger tier. These are variants of the same trained generation rather than extra catalog models. The current H Models API exposes the 35B tier with a 65,536-token hosted context; that limit is described without treating it as a verified uniform specification for every size.

2026-06-02
0.8B, 4B, 9B, and 35B total/3B active language tiers
Qwen-derived dense and hybrid-attention Mixture-of-Experts vision-language Transformers
Apache-2.0
Compare with other models

Specifications

Parameters
0.8B, 4B, 9B, and 35B total/3B active language tiers
Architecture
Qwen-derived dense and hybrid-attention Mixture-of-Experts vision-language Transformers
License
Apache-2.0
Type
multimodal
Modalities
textimage

Benchmark Scores

Advanced Specifications

Model Family
Holo
API Access
Available
Chat Interface
Not Available
Variants
Holo3.1-0.8BHolo3.1-4BHolo3.1-9BHolo3.1-35B-A3BFP8NVFP4Q4 GGUF
Hardware Support
CUDAApple siliconNVIDIA DGX Spark

Capabilities & Limitations

Capabilities
computer usemobile automationnative function callinglocal inference
Known Limitations
Actions require an external computer-use harnessPerformance depends on software environments and evaluation settingsGenerated actions can fail or affect the wrong interface element35B hosted API context is 65,536; a single family-wide context limit is not establishedQuantization and harness choices affect latency and accuracy
Notable Use Cases
private computer assistantsdesktop and mobile automationagents using external tool protocols
Function Calling Support
Yes
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