LLM Reference
NVIDIA NIM

Granite Guardian 3.0 8B on NVIDIA NIM

Granite 3 · IBM Research

ServerlessOpen Source

Last refreshed 2026-05-19. Next refresh: weekly.

Why use Granite Guardian 3.0 8B on NVIDIA NIM?

NVIDIA NIM offers Granite Guardian 3.0 8B with competitive pricing. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.

Input / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: ibm/granite-guardian-3.0-8b
Model ID
ibm/granite-guardian-3.0-8b

Request example

Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID ibm/granite-guardian-3.0-8b.

Gotchas

  • Use provider model ID "ibm/granite-guardian-3.0-8b", not the LLMReference slug "granite-guardian-3.0-8b".

Pricing

TypeRate
GPU Hour Rate$1.00/GPU·hr
GPU Config1xH100

Capabilities

No model capability flags are currently sourced.

About Granite Guardian 3.0 8B

Granite Guardian 3.0 8B is IBM Research's Granite 3 model focused on content moderation and safety classification. It offers an 8K-token context window.

FAQ

What is the context window for Granite Guardian 3.0 8B on NVIDIA NIM?

Granite Guardian 3.0 8B supports a 8k token context window on NVIDIA NIM.

What API model ID do I use for Granite Guardian 3.0 8B on NVIDIA NIM?

Use the model ID ibm/granite-guardian-3.0-8b when calling NVIDIA NIM's API.

Who created Granite Guardian 3.0 8B?

Granite Guardian 3.0 8B was created by IBM Research as part of the Granite 3 model family.

Is Granite Guardian 3.0 8B open source?

Granite Guardian 3.0 8B is open source under Apache 2.0 according to the seed data.

Get Started

Model Specs

Released2025-03-01
Parameters8B
Context8k
ArchitectureDecoder Only
Knowledge cutoff2024-04

Related Models on NVIDIA NIM