Support Matrix for NVIDIA NIM for Object Detection#

This documentation describes the models, software, and hardware that NVIDIA NIM for Object Detection supports.

Models#

Object Detection NIM supports the following models.

Model Name	Model ID	Model Card	Demo / Explore
Nemotron Page Elements v3	`nvidia/nemotron-page-elements-v3`	Model card	Demo
Nemotron Table Structure v1	`nvidia/nemotron-table-structure-v1`	Model card	Demo

Software#

NVIDIA Driver: Ensure that the latest compatible NVIDIA driver is installed on your system before launching NIM containers. If you experience issues starting the containers, verify that your driver is up to date.
NVIDIA Container Toolkit: Your Docker environment must support NVIDIA GPUs. For more information, refer to NVIDIA Container Toolkit.

CPUs#

Release 2.0 supports amd64 and arm64 container architectures. The host CPU architecture must match the container architecture. For a list of supported systems, refer to the NVIDIA Certified Systems Catalog.

Supported Hardware#

Object Detection NIM supports the following GPUs:

GPU	Precision
NVIDIA A100 SXM4 80GB	FP16
NVIDIA A10G	FP16
NVIDIA B200	FP16
NVIDIA GB10 Grace Blackwell Superchip, such as NVIDIA DGX Spark systems	FP16
NVIDIA GB200	FP16
NVIDIA H100 80GB HBM3	FP16
NVIDIA H100 NVL	FP16
NVIDIA H200	FP16
NVIDIA L4	FP16
NVIDIA L40S	FP16
NVIDIA RTX PRO 6000 Blackwell Server Edition	FP16

For the approximate GPU memory size of each GPU, refer to Performance and Memory for NVIDIA NIM for Object Detection.

For details about model profiles and kernel selection, refer to Model Profiles and Kernel Selection.