Agentic AI Reference Architecture

Model Serving · Model asset

Balanced Vision-Language Model

Model assetModel ServingModelsarc:BalancedVisionLanguageModel

A mid-sized vision-language model balancing visual understanding accuracy against compute cost for cloud serving.

Responsibility. Answers questions about images at moderate cost in the cloud.

Also known as: Neva-22B

Variant of Vision-Language Model abstract

When to choose. Choose for cloud deployment needing a balance of accuracy and compute.

specializesalternative toalternative toVision-Language Model: specializesVision-Language ModelEdge Vision-Language Model: alternative toEdge Vision-Language ModelHigh-Accuracy Vision-Language Model: alternative toHigh-Accuracy Vision-Lan…
Direct neighbourhood (hover for relationship types)

Relationships

alternative to variability

Quantitative guidance

As stated by the sources; verify before use.

Classification

Technologies
NVIDIA Neva-22B
Quality attributes
Cost efficiencyFunctional suitability: correctness and validity (ISO/IEC 25010 | NIST AI RMF: valid)

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.