Arrakis / Models / MiniCPM-V-4.7-35B-A3B

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 this model Check another model

What it takes to serve it

GPU memory to run it for inference, with the smallest GPU setup that holds it and the lowest price on Arrakis right now.

Precision	Memory and the smallest setup
16-bit	85 GB: one RTX PRO 6000, from $1.90 per GPU-hour
8-bit	42 GB: one L40S, RTX 6000 Ada or RTX A6000, L40S from $0.44 per GPU-hour
4-bit	21 GB: one RTX 4090 or RTX 3090, RTX 3090 from $0.19 per GPU-hour

What it takes to fine-tune it

QLoRA trains adapters on a 4-bit frozen model, LoRA on a 16-bit one, and full fine-tuning updates every weight. Figures are before activations, which grow with batch size and sequence length.

Method	Memory and the smallest setup
QLoRA	25 GB: one RTX 5090, from $0.58 per GPU-hour
LoRA	85 GB: one RTX PRO 6000, from $1.90 per GPU-hour
Full fine-tuning	563 GB: 4 × H200, from $13.76 per hour for all 4

About the model

From its card and files on Hugging Face. Memory figures here follow the GPU memory guide.

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

Deploy it on Arrakis

Open Models in the console, 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. Or run it yourself on any machine with enough GPU memory:

vLLM

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

Deploy this model How deploying works

Questions

Live prices for every GPU are on the GPU prices page.

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

Every model, and a check for any other.