# MiniMax-M2.7 GPU requirements

MiniMax-M2.7 has 229B parameters. To serve it, plan for about 549 GB of GPU memory in 16-bit, 274 GB in 8-bit or 137 GB in 4-bit, including about 20% for the KV cache and activations.

It is a mixture of experts: 256 experts, 8 of them active for each token. All of them stay in GPU memory, so plan memory for all 229B parameters.

[Deploy it on Arrakis](/console/#/models?model=MiniMaxAI/MiniMax-M2.7).

## What it takes to serve it

| Precision | Memory and the smallest setup |
|---|---|
| 16-bit | 549 GB: 4 × [H200](/gpus/h200.html.md), from $16.12 per hour for all 4 |
| 8-bit | 274 GB: 2 × [H200](/gpus/h200.html.md), from $8.06 per hour for all 2 |
| 4-bit | 137 GB: one [H200](/gpus/h200.html.md), from $4.03 per GPU-hour |

## What it takes to fine-tune it

| Method | Memory and the smallest setup |
|---|---|
| QLoRA | 160 GB: one [B200](/gpus/b200.html.md), from $6.79 per GPU-hour |
| LoRA | 549 GB: 4 × [H200](/gpus/h200.html.md), from $16.12 per hour for all 4 |
| Full fine-tuning | 3,659 GB: more than one 8-GPU machine |

## About the model

| | |
|---|---|
| Parameters | `229B` |
| Experts | `256` |
| Experts for each token | `8` |
| Context window (tokens) | `204,800` |
| Published in | `FP8` |
| License | `other` |
| Released | `2026-04-09` |
| Weights | [MiniMaxAI/MiniMax-M2.7](https://huggingface.co/MiniMaxAI/MiniMax-M2.7) |

## Serve it yourself

```
vllm serve MiniMaxAI/MiniMax-M2.7 --tensor-parallel-size 4
```

## Questions

**How much GPU memory does MiniMax-M2.7 need?** To serve it, about 549 GB in 16-bit, 274 GB in 8-bit, 137 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 160 GB with QLoRA, 549 GB with LoRA and 3,659 GB for full fine-tuning with Adam, before activations.

**Can I run MiniMax-M2.7 on one GPU?** Yes, quantized. In 4-bit it needs about 137 GB, which fits on one H200. In 16-bit it needs 4 H200 GPUs.

**What does it cost to run MiniMax-M2.7?** In 16-bit it needs 4 H200 GPUs; in 4-bit, one H200. Each setup on this page shows the lowest price per GPU-hour on Arrakis right now, and you pay by the hour from a prepaid balance.

**How do I deploy MiniMax-M2.7 on Arrakis?** Open Models in the Arrakis console, paste MiniMaxAI/MiniMax-M2.7, choose vLLM, SGLang or llama.cpp, and rent a GPU it fits on. You get an OpenAI-compatible endpoint with its own API key, and root SSH to the machine.


More models: [/models](/models.html.md).