Agentic AI Reference Architecture

Model Serving · Model asset

Edge Vision-Language Model

Model assetModel ServingModelsarc:EdgeVisionLanguageModel

A compact vision-language model (single-digit billions of parameters) sized to run on embedded edge GPU devices.

Responsibility. Answers questions about images on-device.

Also known as: Neva-7B

Variant of Vision-Language Model abstract

When to choose. Choose for edge deployment on embedded GPU devices where memory and power are constrained.

deployed onspecializesis target of alternativeToEdge GPU Device: deployed onEdge GPU DeviceVision-Language Model: specializesVision-Language ModelBalanced Vision-Language Model: is target of alternativeToBalanced Vision-Language…
Direct neighbourhood (hover for relationship types)

Relationships

deployed on structural

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
NVIDIA Neva-7BNVIDIA Jetson AGX Orin
Quality attributes
Performance efficiency (ISO/IEC 25010)Flexibility (ISO/IEC 25010)

Sources

  1. Ch7.5: T. Nguyen, "NeMo Curator, Riva Speech AI & Multimodal Integration," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 7.5. ISBN: 9798244538229.