Zhipu GLM-4.6V
Cherry Studio users can now, via the built-in CherryIN service for free access Zhipu GLM-4.6V— The visual flagship model released by Z.ai (Zhipu AI) in December 2025, with a MoE architecture, 128K native multimodal context, and native multimodal tool calling, making it the preferred choice for image-text understanding and multimodal Agent scenarios.
What is GLM-4.6V?
GLM-4.6V is the latest-generation vision-language model in Z.ai's GLM-V series, natively supporting unified modeling of text + images, and further expanding context and tool-calling capabilities on the basis of GLM-4.5V.
Architecture: Mixture-of-Experts (MoE)
Total parameters: 106B
Activated parameters: about 12B
Context length: 128K tokens
Open-source license: MIT
Release date: December 8–9, 2025
Visual encoder: supports multi-resolution images (up to 4K)
The series also includes GLM-4.6V-Flash (9B), aimed at local and low-latency scenarios, free for commercial use.
Continues the multimodal training system of the GLM-V series
GLM-4.6V follows the technical path of GLM-4.1V-Thinking / GLM-4.5V, and has been further strengthened in vision and Agent directions:
Native multimodal modeling: jointly trained on text and images, supports mixed text-image input
Context expansion: training context expanded to 128K tokens, capable of processing about 150 pages of dense documents, 200 pages of slides, or 1 hour of video in a single pass
Native multimodal tool calling: tools can directly receive and return images, and multimodal artifacts are handled via URL using the extended MCP protocol
Reinforcement learning enhancement: continues the scalable RL pipeline of the GLM-V series
Native multimodal, designed for real-world scenarios
GLM-4.6V's multimodal capabilities cover both everyday and professional scenarios:
✅ Rich-text content understanding: long documents, multi-page text, and mixed image-text layouts
✅ Visual web search: combined with visual input for web retrieval and understanding
✅ Frontend recreation: generate frontend code from design drafts or UI screenshots
✅ Long-context multimodal document analysis: whole PDF / slide / video-level input
✅ Chart and table parsing: structured information extraction
Native multimodal tool calling and Agent capabilities
One of the core upgrades of GLM-4.6V is "visual perception → executable action" the closed loop: tool calling natively supports images as both input and output, enabling multimodal Agents to be deployed in real business scenarios.
Simple image-text Q&A
Direct conversation
"What's in this picture?"
Medium-complexity tasks
Enable tool calling
Retrieve data after reading charts
Complex multimodal Agent
Multiple tools + MCP
Screenshot → understand → call API → generate report
Efficient MoE, openly available
⚡ MoE sparse activation: 106B total parameters, only about 12B activated
💰 Through CherryIN in Cherry Studio Free to use
🖥️ The weights, inference code, and MCP tools have been open-sourced on GitHub and Hugging Face under the MIT license
Focused on practical capabilities: multimodal assistant
GLM-4.6V is suitable for the following scenarios in real use:
Document assistant: read and summarize long documents, scans, and entire slide decks
Data analysis: identify and interpret chart and dashboard screenshots
Frontend and design: generate or modify frontend code based on UI screenshots
Visual search: combine images for web retrieval and information integration
Multimodal Agent: use tools such as browser, code execution, and retrieval to complete complex tasks
How to use in Cherry Studio?
Open Cherry Studio and go to Settings → Model Services.
Find CherryIN service provider and enable it.
Select Zhipu GLM-4.6V.
Return to the chat interface and switch to GLM-4.6V, you can directly upload images in the conversation for image-text interaction.
💡 Tip: The free model quota provided by CherryIN is covered by Cherry Studio officially, suitable for daily experience and evaluation; for production environments, it is recommended to use the official Z.ai (Zhipu) API.
📘 Try Zhipu GLM-4.6V now and unlock native multimodal and visual Agent capabilities!
Get help and submit feedback
If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.
Last updated
Was this helpful?