Skip to content

Support Matrix for NeMo Retriever Library

Before you begin using NeMo Retriever Library, ensure that you have the hardware for your use case.

Note

NVIDIA Ingest (nv-ingest) has been renamed NeMo Retriever Library.

Core and Advanced Pipeline Features

The Nemo Retriever Library extraction core pipeline features run on a single A10G or better GPU. The core pipeline features include the following:

  • llama-nemotron-embed-1b-v2 — Embedding model for converting text chunks into vectors.
  • nemotron-page-elements-v3 — Detects and classifies images on a page as a table, chart or infographic.
  • nemotron-table-structure-v1 — Detects rows, columns, and cells within a table to preserve table structure and convert to Markdown format.
  • nemotron-graphic-elements-v1 — Detects graphic elements within chart images such as titles, legends, axes, and numerical values.
  • nemotron-ocr-v1 — Image OCR model to detect and extract text from images.
  • retrieval — Enables embedding and indexing into Milvus.

Advanced features require additional GPU support and disk space. This includes the following:

Hardware Requirements

NeMo Retriever Library supports the following GPU hardware.

The following are the hardware requirements to run NeMo Retriever Library.

Feature GPU Option RTX Pro 6000 B200 H200 NVL H100 A100 80GB A100 40GB A10G L40S RTX PRO 4500 Blackwell
GPU Memory 96GB 180GB 141GB 80GB 80GB 40GB 24GB 48GB 32GB GDDR7 (GB203)
Core Features Total GPUs 1 1 1 1 1 1 1 1 1
Core Features Total Disk Space ~150GB ~150GB ~150GB ~150GB ~150GB ~150GB ~150GB ~150GB ~150GB
Audio (parakeet-1-1b-ctc-en-us) Additional Dedicated GPUs 1 1 1 1 1 1 1 1
Audio (parakeet-1-1b-ctc-en-us) Additional Disk Space ~37GB ~37GB ~37GB ~37GB ~37GB ~37GB ~37GB ~37GB ~37GB¹
nemotron-parse Additional Dedicated GPUs Not supported Not supported Not supported 1 1 1 1 1 Not supported²
nemotron-parse Additional Disk Space Not supported Not supported Not supported ~16GB ~16GB ~16GB ~16GB ~16GB Not supported²
VLM Additional Dedicated GPUs 1 1 1 1 1 Not supported Not supported 1 Not supported³
VLM Additional Disk Space ~16GB ~16GB ~16GB ~16GB ~16GB Not supported Not supported ~16GB Not supported³
Reranker With Core Pipeline Yes Yes Yes Yes Yes No* No* No* No*
Reranker Standalone (recall only) Yes Yes Yes Yes Yes Yes Yes Yes Yes

¹ Audio runs but requires runtime engine build — no pre-defined model profile.

² Nemotron Parse fails to start on 32GB, pending engineering investigation.

³ VLM fails to load on 32GB, 32GB is below the minimum threshold.

* GPUs with less than 80GB VRAM cannot run the reranker concurrently with the core pipeline. To perform recall testing with the reranker on these GPUs, shut down the core pipeline NIM microservices and run only the embedder, reranker, and your vector database.