# OpenBMB's MiniCPM-V 4.7 brings MoE to vision models

> The new 35B-parameter vision-language model activates just 3B parameters per pass, aiming for efficiency without sacrificing capability.

Published by The Open Weights on Oct 7, 2026. Canonical: https://theopenweights.com/news/minicpm-v-4-7-35b-a3b-92zl

## Key facts

- Company: OpenBMB
- Model: MiniCPM-V-4.7-35B-A3B
- Version: 4.7
- Category: Vision-Language
- Modalities: Vision-Language
- License: Apache 2.0 (Open weights, commercial use allowed)
- Parameters: 35B (mixture of experts)
- Active parameters: 3B
- Context window: 262K tokens
- Architecture: MiniCPMV4_7ForConditionalGeneration
- Precision: BF16
- Weights size: 70.4 GB
- Significance: notable
- Published: 2026-10-07
- Last verified: 2026-10-13
- Hugging Face: https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B
- Canonical URL: https://theopenweights.com/news/minicpm-v-4-7-35b-a3b-92zl

OpenBMB has released [MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B), the latest entry in its MiniCPM-V line of multimodal models. The headline detail is architectural: this is a mixture-of-experts (MoE) vision-language model with 35 billion total parameters but only about 3 billion active on any given forward pass.

That design is the whole point. MoE lets a model hold a large pool of specialized parameters while routing each input through a small fraction of them, keeping inference costs closer to a 3B dense model than a 35B one. For a vision-language system, where image understanding typically adds significant compute, that efficiency can be the difference between a model that runs comfortably on modest hardware and one that doesn't.

## Why it matters

The MiniCPM-V series has built a reputation for packing strong multimodal performance into compact footprints, and version 4.7 extends that philosophy with an MoE twist. Key points from the release:

- 35B total parameters with roughly 3B active per inference
- A vision-language focus, handling image and text inputs together
- Permissive Apache 2.0 licensing, allowing commercial use

The permissive license is notable for teams weighing deployment. Apache 2.0 removes much of the friction that accompanies more restrictive open-weight releases, making MiniCPM-V 4.7 a candidate for products as well as research.

OpenBMB has not published full benchmark details in the record here, so real-world evaluation will determine how the sparse-activation approach compares to dense peers. But the direction is clear: efficient multimodal models that trade raw size for smart routing. The weights are available now on [Hugging Face](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B).

## Get the model

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

## Sources

- [openbmb/MiniCPM-V-4.7-35B-A3B](https://huggingface.co/openbmb/MiniCPM-V-4.7-35B-A3B) — Hugging Face, Oct 7, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "OpenBMB's MiniCPM-V 4.7 brings MoE to vision models", The Open Weights, Oct 7, 2026, https://theopenweights.com/news/minicpm-v-4-7-35b-a3b-92zl