Holotron-12B
Holotron-12B is H Company’s first Holotron computer-use model, developed with NVIDIA and post-trained from Nemotron Nano 2 VL. The approximately 12B hybrid state-space/attention vision-language model is optimized for production throughput, long interactive histories, and multiple screenshots. Targeted training turns the general multimodal backbone into an agent policy that interprets screens and emits actions across web, desktop, and mobile environments. The released model card explicitly dates publication to March 16 and identifies NVIDIA model licensing. Public weights allow local experimentation; an external harness supplies screenshots, executes actions, and manages the agent loop. Benchmark throughput is specific to the tested GPU and workload configuration.
Specifications
- Parameters
- Approximately 12B
- Architecture
- Hybrid state-space/attention vision-language model
- License
- NVIDIA Open Model License
- Type
- multimodal
- Modalities
- textimage
Benchmark Scores
Advanced Specifications
- Model Family
- Holotron
- Finetuned From
- NVIDIA Nemotron Nano 12B v2 VL
- API Access
- Not Available
- Chat Interface
- Not Available
- Hardware Support
- CUDANVIDIA H100
Capabilities & Limitations
- Capabilities
- computer usemultimodal agent policyvisual groundinghigh-throughput 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 elementNVIDIA weight terms applyServing throughput depends on GPU, concurrency, and screenshot workload
- Notable Use Cases
- computer-use researchagent data generationprivate workflow automation
- Tool Use Support
- Yes