Runtime as featured inForbesRead the article
MiniMax M3.1 Flash specs
MiniMax logo

How to run MiniMax M3.1 Flash

Bedrock, Vertex AI, or your own GPUs · Checked November 21, 2026

MiniMax M3.1 Flash has 428B parameters, so it needs about 1,028GB of GPU memory at full precision and about 514GB at FP8. A practical starting point is FP8 on 8x 80GB GPUs.

You have three ways to run it: a managed host that already serves it, your own GPUs in your cloud, or both behind one endpoint. Then you point your agents at it. Here is what each path takes.

MiniMax M3.1 Flash hardware requirements

PrecisionMemory neededSmallest setup that fits
BF16 (full precision)~1,028GB8x 141GB GPUs (one H200 node)
FP8~514GB8x 80GB GPUs (one H100 node)
4-bit quantized~257GB4x 80GB GPUs

Our estimates: 428B parameters times bytes per parameter, plus 20% for the KV cache and the serving runtime. As a mixture-of-experts model, MiniMax M3.1 Flash activates only 23B per token, which makes it fast, but every expert still has to sit in memory. Using the full 1M-token context needs more. Check the model card for the precision the weights ship in and any recommended settings.

Where to run MiniMax M3.1 Flash

01Amazon Bedrock

Not confirmed as of November 21, 2026

We could not confirm MiniMax M3.1 Flash in the Bedrock model catalog. To keep it in AWS anyway, serve it yourself on GPU instances in your account (EC2 or SageMaker) with the setup below, and check the Bedrock catalog again: new open models are added often.

02Google Cloud Vertex AI

Not confirmed as of November 21, 2026

We could not confirm MiniMax M3.1 Flash in Vertex AI Model Garden. To keep it in Google Cloud, serve it yourself on GPUs in your project (GKE or Compute Engine) with the setup below.

03Self-host on your own GPUs

vLLM support confirmed

Download MiniMaxAI/MiniMax-M3.1-Flash from Hugging Face and serve it with an inference server that exposes an OpenAI-compatible endpoint. vLLM support it. Start with FP8 on 8x 80GB GPUs (one H100 node), then load-test with your real prompts before you size for production.

  • Keep the endpoint private to your VPC, so prompts and payment data never leave your cloud.
  • Read the MiniMax Community License before you deploy, since custom licenses can carry conditions.
  • Run two replicas or keep a hosted model as a fallback, so agents keep working during an upgrade.

Run MiniMax M3.1 Flash with Runtime

Serving the model is half the job. The other half is giving agents a safe place to use it. Runtime is the AI agent harness for payment and fintech teams, and it is model-neutral: connect MiniMax M3.1 Flash from Bedrock, Vertex AI, or your own endpoint, and your agents use it next to Claude, GPT, or Gemini.

  • In your cloud. Runtime runs in your AWS, GCP, or Azure account or fully self-hosted, next to the model.
  • Routed by evals. Evals show which steps MiniMax M3.1 Flash handles as well as a frontier model, so routine work moves to the cheaper model.
  • Fallbacks. If your endpoint is down or slow, agents fall back to another model instead of stopping.
  • Guardrails. Agents start read-only, wait for approval before money moves, and every run is recorded.

Harnesses that can drive MiniMax M3.1 Flash on Runtime:

Claude CodeOpenCodeCline

Running MiniMax M3.1 Flash: FAQ

How much GPU memory does MiniMax M3.1 Flash need?

+

About 1028GB at BF16, 514GB at FP8, and 257GB at 4 bits. These are our estimates: the weights plus 20% headroom. Long contexts need more memory for the KV cache.

What is the cheapest way to self-host MiniMax M3.1 Flash?

+

Start with FP8 on 8x 80GB GPUs (one H100 node). Quantizing further saves memory but can cost accuracy, so test it on your own tasks first.

Is MiniMax M3.1 Flash available on Amazon Bedrock?

+

As of November 21, 2026, we could not confirm MiniMax M3.1 Flash in the Bedrock model catalog. You can still run it in your AWS account on your own GPU instances (EC2 or SageMaker) with vLLM.

Is MiniMax M3.1 Flash available on Google Vertex AI?

+

As of November 21, 2026, we could not confirm MiniMax M3.1 Flash in Vertex AI Model Garden. You can still run it in your Google Cloud project on your own GPUs (GKE or Compute Engine) with vLLM.

Can I use MiniMax M3.1 Flash with Runtime?

+

Yes. Runtime is model-neutral. Serve MiniMax M3.1 Flash from Bedrock, Vertex AI, or your own endpoint, connect it to Runtime, and agents use it through a harness like Claude Code. Your data stays in your cloud, and evals tell you which steps it can take over from a more expensive model.