# Zhipu AI Releases Fast, Open Vision Model GLM-4.6V-Flash

> The new model from the GLM-4.6V family offers a fast, MIT-licensed option for developers working with both text and images.

Published by The Open Weights on Dec 7, 2025. Canonical: https://theopenweights.com/news/glm-4-6v-flash-9rt7

## Key facts

- Company: Zhipu AI
- Model: GLM-4.6V-Flash
- Version: 4.6V-Flash
- Category: Vision-Language
- Modalities: Vision-Language
- License: MIT (Open weights, commercial use allowed)
- Context window: 131K tokens
- Architecture: Glm4vForConditionalGeneration
- Precision: BF16
- Weights size: 20.6 GB
- Significance: notable
- Published: 2025-12-07
- Last verified: 2026-06-17
- Hugging Face: https://huggingface.co/zai-org/GLM-4.6V-Flash
- Canonical URL: https://theopenweights.com/news/glm-4-6v-flash-9rt7

Zhipu AI has released [GLM-4.6V-Flash](https://huggingface.co/zai-org/GLM-4.6V-Flash), a new open-source vision-language model. As its name suggests, this "Flash" version is designed for speed and efficiency, joining the company's growing GLM-4.6V family of multimodal models.

The model's most significant feature for the open-source community is its permissive MIT license. This allows for broad adoption, including in commercial products, without the usage restrictions common to many research-oriented releases. This choice lowers the barrier for developers looking to build and deploy applications that can understand both images and text.

While technical details like parameter count and architecture specifics were not detailed in the initial release card, GLM-4.6V-Flash's focus on performance is clear. It provides another strong alternative in the competitive landscape of open vision-language models, particularly for use cases where low latency is a key requirement, such as real-time visual analysis or interactive chatbots.

This release solidifies Zhipu AI's position as a consistent contributor to the open-source ecosystem. By providing a fast, commercially-friendly VLM, the company offers developers a valuable new tool for building the next wave of multimodal applications.

## Get the model

- [Hugging Face](https://huggingface.co/zai-org/GLM-4.6V-Flash)

## Sources

- [zai-org/GLM-4.6V-Flash](https://huggingface.co/zai-org/GLM-4.6V-Flash) — Hugging Face, Dec 7, 2025

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Zhipu AI Releases Fast, Open Vision Model GLM-4.6V-Flash", The Open Weights, Dec 7, 2025, https://theopenweights.com/news/glm-4-6v-flash-9rt7