# MiniCPM-V-4.7-35B-A3B GPU requirements

MiniCPM-V-4.7-35B-A3B has 35B parameters. To serve it, plan for about 85 GB of GPU memory in 16-bit, 42 GB in 8-bit or 21 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 35B parameters.

[Deploy it on Arrakis](/console/#/models?model=openbmb/MiniCPM-V-4.7-35B-A3B).

## What it takes to serve it

| Precision | Memory and the smallest setup |
|---|---|
| 16-bit | 85 GB: one [RTX PRO 6000](/gpus/rtx-pro-6000.html.md), from $1.90 per GPU-hour |
| 8-bit | 42 GB: one [L40S](/gpus/l40s.html.md), [RTX 6000 Ada](/gpus/rtx-6000-ada.html.md) or [RTX A6000](/gpus/rtx-a6000.html.md), L40S from $0.44 per GPU-hour |
| 4-bit | 21 GB: one [RTX 4090](/gpus/rtx-4090.html.md) or [RTX 3090](/gpus/rtx-3090.html.md), RTX 3090 from $0.19 per GPU-hour |

## What it takes to fine-tune it

| Method | Memory and the smallest setup |
|---|---|
| QLoRA | 25 GB: one [RTX 5090](/gpus/rtx-5090.html.md), from $0.58 per GPU-hour |
| LoRA | 85 GB: one [RTX PRO 6000](/gpus/rtx-pro-6000.html.md), from $1.90 per GPU-hour |
| Full fine-tuning | 563 GB: 4 × [H200](/gpus/h200.html.md), from $16.12 per hour for all 4 |

## About the model

| | |
|---|---|
| Parameters | `35B` |
| Active for each token | `3B` |
| Experts | `256` |
| Experts for each token | `8` |
| Context window (tokens) | `262,144` |
| Published in | `BF16` |
| License | `apache-2.0` |
| Released | `2026-10-07` |
| Weights | [openbmb/MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B) |

## Serve it yourself

```
vllm serve openbmb/MiniCPM-V-4.7-35B-A3B --tensor-parallel-size 1
```

## Questions

**How much GPU memory does MiniCPM-V-4.7-35B-A3B need?** To serve it, about 85 GB in 16-bit, 42 GB in 8-bit, 21 GB in 4-bit, including about 20% for the KV cache and activations. To fine-tune it, about 25 GB with QLoRA, 85 GB with LoRA and 563 GB for full fine-tuning with Adam, before activations.

**Can I run MiniCPM-V-4.7-35B-A3B on one GPU?** Yes. In 16-bit it needs about 85 GB, which fits on one RTX PRO 6000.

**What does it cost to run MiniCPM-V-4.7-35B-A3B?** In 16-bit it needs one RTX PRO 6000; in 4-bit, one RTX 4090 or RTX 3090. 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 MiniCPM-V-4.7-35B-A3B on Arrakis?** Open Models in the Arrakis console, paste openbmb/MiniCPM-V-4.7-35B-A3B, 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).