Image + text

CogVLM и GLM-V

Vision models from Zhipu: first CogVLM, then the GLM-V line. GLM-4.6V can call tools based on images and act as an agent operating an interface.

Developer
Zhipu AI (Z.ai) and Tsinghua University, China
First release
Nov 2023
Latest release
Dec 2025
Sizes
9B – 106B-A12B
License
Commercial use allowedGLM-4.1V / 4.5V / 4.6V: MIT; CogVLM and CogVLM2: their own licenses (CogVLM2 is based on Llama 3)
Russian
Not supported
Running
On your own serverNeeds a GPU
Industries
Documents and accounting, Science and research
Deploy on your server Hugging Face GitHub

What it does

  • Answering questions about photos and documents
  • An agent that operates an interface from screenshots
  • Analysing charts and reports
  • Captions for photos and video

Where it is used

Document workflowCustomer supportAnalytics

Hardware requirements

LaptopLaptop or regular PC, up to 8 GB of VRAM — smaller versions
fits
1 GPUOne GPU with 16–80 GB — mid-size versions
fits
ClusterServer with several GPUs — flagship versions
fits

Versions

  1. GLM-4.6V и GLM-4.6V-Flash 9B
  2. GLM-4.5V 106B-A12B
  3. GLM-4.1V-9B-Thinking
  4. CogVLM2 19B
  5. CogAgent
  6. CogVLM-17B

How to run it

On your own serverWeights are downloaded from Hugging Face and served with vLLM (load and API) or llama.cpp (modest hardware). The model then runs in a closed network with no per-request fees.Hugging Face
How much hardware you needCalculate the VRAM for the model size, context length and number of concurrent requests.Open the hardware calculator

I can set this up end to end: pick the model size, deploy it on your server and connect it to your systems.

Frequently asked questions

Can CogVLM и GLM-V be used in a commercial project?

Yes. License: GLM-4.1V / 4.5V / 4.6V: MIT; CogVLM and CogVLM2: their own licenses (CogVLM2 is based on Llama 3). It allows commercial use, but it is still worth having a lawyer review the license before launch.

What hardware does CogVLM и GLM-V need?

At minimum: Laptop or regular PC, up to 8 GB of VRAM — smaller versions. Without a GPU the model is not practical. You can calculate the exact VRAM for your model size and context in the hardware calculator.

Does CogVLM и GLM-V support Russian?

No. The model card lists its languages and Russian is not among them.

Where can I download CogVLM и GLM-V and what does it cost?

The CogVLM и GLM-V weights are open and free to download. You only pay for the hardware it runs on and for the setup. Source links are at the bottom of this page.

How I deploy it for clients

  1. SelectionI pick the model size for your task and hardware and test it on your examples.
  2. DeploymentI deploy it on your server or in a closed network and provide an API.
  3. Fine-tuningI fine-tune it on your data (LoRA) or connect a knowledge base — whichever is cheaper for the task.
  4. IntegrationI connect it to your CRM, ERP, bot, website or team chat and set up monitoring.

Similar models

TextGLM (ChatGLM)Zhipu AI (Z.ai) · ChinaCommercial use with conditions

One of the oldest Chinese open lines: from ChatGLM-6B to GLM-5.3. Strong at agentic tasks and programming; GLM-5.3-Flash understands images and is released under MIT.

DetailsImage + textQwen-VLAlibaba (Qwen team) · ChinaCommercial use allowed

One of the strongest open vision models: reads documents, tables, charts and video, and works with user interfaces. Since Qwen3.5, vision is built directly into the main Qwen model.

DetailsDocuments and OCRGLM-OCRZhipu AI (Z.ai) · ChinaCommercial use allowed

A lightweight OCR model from Zhipu for document parsing. The model card lists Russian among supported languages; built for high load and low-end hardware.

Details

Source: huggingface.co/zai-org/GLM-4.6V. Data checked against the model card on 22 Sep 2026. Have a lawyer review the license before commercial launch.