> This page is for MSA Search, version 3.0.0 (Latest) (default).
> For other versions, use one of these documentation indexes:
> - 3.0.0 (Latest) (default): https://docs.nvidia.com/nim/bionemo/msa-search/3.0.0/llms.txt
> - 2.6.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.6.0/llms.txt
> - 2.5.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.5.0/llms.txt
> - 2.4.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.4.0/llms.txt
> - 2.3.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.3.0/llms.txt
> - 2.2.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.2.0/llms.txt
> - 2.1.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.1.0/llms.txt
> - 2.0.0: https://docs.nvidia.com/nim/bionemo/msa-search/2.0.0/llms.txt
> - 1.0.0: https://docs.nvidia.com/nim/bionemo/msa-search/1.0.0/llms.txt

> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.nvidia.com/nim/bionemo/llms.txt.

# MSA Search Support Matrix

> Supported NVIDIA GPUs, hardware requirements, and software prerequisites for the MSA Search NIM.

This page lists the minimum system hardware requirements and the NVIDIA GPUs supported for deploying the MSA Search NIM.

## Supported Hardware

The following sections describe the minimum system hardware requirements and the supported NVIDIA GPUs.

### Minimum System Hardware Requirements

| CPU Cores | RAM (GB) | NVMe SSD Storage (GB) | GPU Count                                              |
|-----------|----------|-----------------------|--------------------------------------------------------|
| 24        | 64       | 1,660                 | One or more NVIDIA GPUs from the Supported NVIDIA GPUs |

### Supported NVIDIA GPUs

The MSA Search NIM supports NVIDIA GPUs with at least 48 GB of GPU memory.
It has been tested on the following recommended configurations:

| GPU                      | GPU Memory (GB) | GPU Count |
|--------------------------|-----------------|-----------|
| NVIDIA A100-SXM4-80GB    | 80              | 1-8       |
| NVIDIA H100 80GB HBM3    | 80              | 1-8       |
| NVIDIA H200              | 141             | 1-8       |
| NVIDIA B200              | 180             | 1-8       |
| NVIDIA B300              | 288             | 1-8       |
| NVIDIA GB200             | 186             | 1-8       |
| NVIDIA GB300             | 288             | 1-8       |
| NVIDIA GH200 144GB       | 144             | 1-8       |
| NVIDIA GB10 (DGX Spark)  | 128             | 1         |
| NVIDIA L40S              | 48              | 2-8       |
| NVIDIA RTX 6000 Ada Generation | 48        | 2-4       |

<Note>
- Starting with version 2.0.0, GPUs with 48 GB memory (NVIDIA L40S, NVIDIA RTX 6000 Ada Generation) require a minimum of 2 GPUs when using GPU Server (enabled by default). This is because GPU Server holds databases in memory for optimal performance.
- Starting with version 2.4.0, the MSA Search NIM adds support for NVIDIA H200, NVIDIA GH200 144GB, NVIDIA GB200, and NVIDIA GB300. NVIDIA GH200 144GB, NVIDIA GB200, and NVIDIA GB300 are Grace-based platforms (Hopper or Blackwell GPU with NVIDIA Grace CPU). Use container images and host OS builds intended for your CPU architecture (aarch64/arm64 on Grace systems, x86_64/amd64 on typical x86 servers).
- Starting with version 2.5.0, the MSA Search NIM adds support for NVIDIA B300 and NVIDIA GB10 (DGX Spark). NVIDIA GB10 (DGX Spark) uses 128 GB of unified memory shared across CPU and GPU on the Grace Blackwell Superchip architecture. Use aarch64/arm64 container images and host OS builds for NVIDIA GB10 (DGX Spark) deployments.
</Note>

## Software Prerequisites

* Begin with Linux-based [Docker-supported operating system](https://docs.docker.com/engine/install/#installation-procedures-for-supported-platforms)
* Install [Docker](https://docs.docker.com/engine/install/) - minimum version: 23.0.1
* Install [NVIDIA Drivers](https://www.nvidia.com/en-us/drivers/) - minimum version: 580
* Install the [NVIDIA Container Toolkit](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/install-guide.html#installing-the-nvidia-container-toolkit) - minimum version: 1.13.5
* Verify your container runtime supports NVIDIA GPUs by running

```bash
docker run --rm --runtime=nvidia --gpus all ubuntu nvidia-smi
```

Example output:

```bash
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 580.82.07    Driver Version: 580.82.07    CUDA Version: 13.0     |
|-------------------------------+----------------------+----------------------+
| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
|                               |                      |               MIG M. |
|===============================+======================+======================|
|   0  NVIDIA H100 ...     On  | 00000000:1B:00.0 Off |                    0 |
| N/A   33C    P0             75W /  700W |       1MiB /  81559MiB |      0%      Default |
|                               |                      |             Disabled |
+-------------------------------+----------------------+----------------------+

+-----------------------------------------------------------------------------+
| Processes:                                                                  |
|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |
|        ID   ID                                                   Usage      |
|=============================================================================|
|  No running processes found                                                 |
+-----------------------------------------------------------------------------+
```

<Note>
For more information on enumerating multi-GPU systems, refer to the NVIDIA Container Toolkit's [GPU Enumeration Docs](https://docs.nvidia.com/datacenter/cloud-native/container-toolkit/latest/docker-specialized.html#gpu-enumeration).
</Note>

Supported CPU architectures: x86_64 / amd64 for typical discrete-GPU servers, and aarch64 / arm64 for NVIDIA Grace-based platforms (NVIDIA GH200 144GB, NVIDIA GB200, NVIDIA GB300, NVIDIA GB10 (DGX Spark)) when using the corresponding container images.