LLM Reference

NemoGuard Models by NVIDIA AI

2 models2025Up to 4k ctx

About

NemoGuard is NVIDIA's family of safety and content moderation models built on Llama, designed to detect unsafe content and enforce topic restrictions in LLM applications.

Current Variants

Use-when guidance is derived from seed capabilities, context, release, and replacement fields.

2 in view

Use when the workload needs safety, 4k context, and 8B parameters.

2025-01safety4k context8B parameters

Use when the workload needs safety, 4k context, and 8B parameters.

2025-01safety4k context8B parameters

Release Timeline

1 release group
2025-01
2 current
Llama 3.1 NemoGuard 8B Content Safety
safety4k context8B parameters
Current
Llama 3.1 NemoGuard 8B Topic Control
safety4k context8B parameters
Current

Specifications(2 models)

NemoGuard model specifications comparison
ModelReleasedContextParameters
Llama 3.1 NemoGuard 8B Content Safety2025-014k8B
Llama 3.1 NemoGuard 8B Topic Control2025-014k8B

Available From(1 provider)

Frequently Asked Questions

What is NemoGuard used for?
NemoGuard is used for safety. The family description and listed model capabilities point to those workloads as the best fit.
How does NemoGuard compare to NVIDIA Nemotron Nano 12B v2 VL?
NemoGuard by NVIDIA AI is strongest where you need safety, while NVIDIA Nemotron Nano 12B v2 VL by NVIDIA AI is the closest related family to check for structured outputs. NemoGuard has 2 listed variants and reaches up to 4k context, so compare the specs and pricing tables before choosing a production model.
Which NemoGuard model should I use?
If price is the main constraint, use the pricing table first because NemoGuard does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate Llama 3.1 NemoGuard 8B Content Safety with 4k context.

Models(2)