deepseek-r1-distill-llama-8b

Prerequisites

• NVIDIA GeForce RTX 4080 or above (see supported GPUs)
• Install the latest NVIDIA GPU Driver on Windows (Version 570+)
• Ensure virtualization is enabled in the system BIOS. In Windows, open Task Manager, select the Performance tab, and find Virtualization. If Disabled, see here to enable.

Experience via App

| ChatRTX | AnythingLLM | AI Toolkit for VSCode|

Open the Windows Subsystem for Linux 2 - WSL2 - Distro

Install WSL2. For additional instructions refer to the documentation.

Once installed, open the NVIDIA-Workbench WSL2 distro using the following command in the Windows terminal.

Copy Code
wsl -d NVIDIA-Workbench -u root

Run the Container

Copy Code
$ podman login nvcr.io
Username: $oauthtoken
Password: <PASTE_API_KEY_HERE>

Pull and run the NVIDIA NIM with the command below. This will download the optimized model for your infrastructure.

Copy Code
export NGC_API_KEY=<PASTE_API_KEY_HERE>
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
chmod -R a+w "$LOCAL_NIM_CACHE"
podman run -it --rm \
    --device nvidia.com/gpu=all \
    --shm-size=16GB \
    -e NGC_API_KEY=$NGC_API_KEY \
    -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
    -e NIM_RELAX_MEM_CONSTRAINTS=1 \
    -u $(id -u) \
    -p 8000:8000 \
    nvcr.io/nim/deepseek-ai/deepseek-r1-distill-llama-8b:1.8.0-RTX

Test the NIM

You can now make a local API call using this curl command:

Copy Code
curl -X 'POST' \
'http://0.0.0.0:8000/v1/chat/completions' \
-H 'accept: application/json' \
-H 'Content-Type: application/json' \
-d '{
    "model": "deepseek-ai/deepseek-r1-distill-llama-8b",
    "messages": [{"role":"user", "content":"Which number is larger, 9.11 or 9.8?"}],
    "max_tokens": 64
}'

For more details on getting started with this NIM, visit the NVIDIA NIM Docs