MiniMax-M3.1-Flash Recipes

Description

Validated, ready-to-apply launch configurations ("recipe") for serving MiniMaxAI/MiniMax-M3.1-Flash with the SGLang Model-Free NIM container. Each recipe is a YAML file for one GPU type and topology. Pass it to the container with NIM_CONFIG_FILE, and the container starts with the exact settings NVIDIA validated.

Recipe file names follow {gpu}_{profile}_{precision}_tp{N}.yaml. Select the corresponding recipe that matches your deployment environment.

Version

Recipe's version equals the container tag it was validated with. For example, recipe 2.1.7-variant is for container sglang-model-free-nim:2.1.7-variant.

Do NOT mix versions. A recipe may set engine options that another container version does not have, or that behave differently.

Deployment Details

Step 1: Download recipe and pick one that matches your GPU.

ngc registry resource download-version "nim/nvidia/<recipe-resource>:<version>"
export RECIPE="$PWD/<recipe-resource>_v<version>/<recipe-file>.yaml"

Step 2: Mount the file into container and deploy

export IMAGE=nvcr.io/nim/nvidia/sglang-model-free-nim-experimental:<version>
export NIM_MODEL_PATH="hf://MiniMaxAI/MiniMax-M3.1-Flash"
export HF_TOKEN="hf_xxx"
export LOCAL_NIM_CACHE=~/.cache/nim
mkdir -p "$LOCAL_NIM_CACHE"
chmod -R a+rwxt "$LOCAL_NIM_CACHE"

docker run --gpus='"device=0,1,2,3"'  \
  -e NIM_MODEL_PATH=$NIM_MODEL_PATH \
  -e HF_TOKEN=$HF_TOKEN \
  -v "$LOCAL_NIM_CACHE:/opt/nim/.cache" \
  -v "$RECIPE:/opt/nim/recipe.yaml:ro" \
  -e NIM_CONFIG_FILE="/opt/nim/recipe.yaml" \
  -p 8000:8000 \
  $IMAGE

Get Help

Getting started with the NIM

Deploying and integrating the NIM is straightforward thanks to our industry standard APIs. Visit the NIM Container page for release documentation, deployment guides and more NIM Container LLM.

Enterprise Support

Get access to knowledge base articles and support cases or submit a ticket.