# MiniCPM-V 4.7 brings a 35B MoE vision model on-device

> OpenBMB's latest multimodal release activates just 3B parameters per token, aiming to keep capable image understanding local.

Published by The Open Weights on Oct 6, 2026. Canonical: https://theopenweights.com/news/minicpm-v-4-7-35b-a3b-93vb

## Key facts

- Company: OpenBMB
- Model: MiniCPM-V 4.7 35B-A3B
- Version: 4.7
- Category: Vision-Language
- Modalities: Vision-Language
- License: Other (Open weights, commercial use allowed)
- Parameters: 35B (mixture of experts)
- Active parameters: 3B
- Context window: 262K tokens
- Architecture: qwen35moe
- Significance: notable
- Published: 2026-10-06
- Last verified: 2026-10-20
- Hugging Face: https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf
- Canonical URL: https://theopenweights.com/news/minicpm-v-4-7-35b-a3b-93vb

OpenBMB has released **MiniCPM-V 4.7**, the newest version of its on-device multimodal line, as a mixture-of-experts vision-language model. The configuration pairs 35 billion total parameters with roughly 3 billion active per token, a design meant to deliver the capacity of a larger model while keeping the per-inference compute cost closer to a small one.

The model is distributed in GGUF format on [Hugging Face](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf), the quantized packaging favored by local runtimes like llama.cpp and Ollama. That choice signals the intended audience: developers who want to run image understanding on laptops, workstations, or edge hardware rather than calling a hosted API.

## Why it matters

MiniCPM-V has built a following by targeting the practical middle ground between tiny toy models and server-only giants. A sparse MoE approach extends that logic:

- **Higher ceiling:** 35B total parameters give the model more knowledge to draw on.
- **Lower active cost:** only about 3B parameters fire per token, easing memory and speed demands.
- **Local-first delivery:** GGUF builds make it straightforward to run offline.

As with prior MiniCPM releases, the model ships under a custom license, so teams should review the terms before commercial use. OpenBMB has not published full context-length or benchmark details in this record, but the release continues the project's focus on bringing capable multimodal reasoning to hardware people actually own.

## Get the model

- [Hugging Face](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf)

## Sources

- [openbmb/MiniCPM-V-4.7-35B-A3B-gguf](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B-gguf) — Hugging Face, Oct 6, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "MiniCPM-V 4.7 brings a 35B MoE vision model on-device", The Open Weights, Oct 6, 2026, https://theopenweights.com/news/minicpm-v-4-7-35b-a3b-93vb