> This page is for version 1.10.1 (default).
> For other versions, use one of these documentation indexes:
> - 1.10.1 (default): https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-contentsafety/1.10.1/llms.txt
> - 1.0.0: https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-contentsafety/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/llama-3-1-nemoguard-8b-contentsafety/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.nvidia.com/nim/llama-3-1-nemoguard-8b-contentsafety/_mcp/server.

# Support Matrix

> The models for NVIDIA NIM microservices use model engines that are tuned for specific NVIDIA GPU models, number of GPUs, precision, and so on. NVIDIA produces model engines for several popular combina

## About Model Profiles

NVIDIA NIM microservices use model engines tuned for specific GPU models, GPU counts, precision, and other settings. These combinations are called *model profiles*. Each profile has a unique 64-character hexadecimal profile ID. The NIM selects a profile automatically based on available GPUs or can use a profile ID that you specify.

The model manifest is stored at `/opt/nim/etc/default/model_manifest.yaml` in the container.

## NVIDIA Llama 3.1 NemoGuard 8B ContentSafety Model Profiles

The model requires 48 GB of GPU memory. NVIDIA developed and tested the microservice using these GPUs:

* B200
* H200
* H100
* H100 NVL
* A100
* A100 SXM4 40 GB
* A10G
* L40S
* A6000

You can use one GPU with the required capacity or two GPUs that meet the capacity. For details about locally buildable and generic model profiles, see [NIM for LLMs model profiles](https://docs.nvidia.com/nim/large-language-models/latest/profiles.html).

### Locally Buildable Model Profiles

| Precision | Tensor parallelism | Engine                           | Profile ID                                                         |
| --------- | -----------------: | -------------------------------- | ------------------------------------------------------------------ |
| BF16      |                  2 | TensorRT-LLM (locally buildable) | `375dc0ff86133c2a423fbe9ef46d8fdf12d6403b3caa3b8e70d7851a89fc90dd` |
| BF16      |                  4 | TensorRT-LLM (locally buildable) | `54946b08b79ecf9e7f2d5c000234bf2cce19c8fee21b243c1a084b03897e8c95` |
| BF16      |                  1 | TensorRT-LLM (locally buildable) | `ac34857f8dcbd174ad524974248f2faf271bd2a0355643b2cf1490d0fe7787c2` |

### Generic Model Profiles

| Precision | Tensor parallelism | Engine | Profile ID                                                         |
| --------- | -----------------: | ------ | ------------------------------------------------------------------ |
| BF16      |                  1 | vLLM   | `4f904d571fe60ff24695b5ee2aa42da58cb460787a968f1e8a09f5a7e862728d` |
| BF16      |                  2 | vLLM   | `7fa4a5a68c0338f16aef61de94977acfdacb7cabd848d38c49c48d2f639f04b3` |
| BF16      |                  4 | vLLM   | `c84b2a068e56a551906563035ed77f88c88cbe1a63c6768fb2d4a9e0af1e67ba` |