LLM
GA
Open source
GLM-4.5V
Open image/video understanding and GUI agent
Release2025-08
Context66K
Max output—
Parameters106B
Local / VRAM80–160 GB
LicenseOpen source
Overview
GLM-4.5V is a model in the LLM category from Z.ai (Zhipu AI). It was released in 2025-08. The vendor is based in China. Best for: Open image/video understanding and GUI agent.
Strengths
- MIT
- Video input
- Strong OCR
Limits
- 64K context
- Large hardware footprint
Specifications
| Vendor | Z.ai (Zhipu AI) |
|---|---|
| Category | LLM |
| Release | 2025-08 |
| Status | GA |
| License | Open source |
| License name | MIT |
| Commercial use | Allowed |
| Parameters | 106B |
| Active parameters | 12B |
| Architecture | MoE VLM |
| Context window | 66K |
| Input modalities | Text, Image, Video |
| Output modalities | Text |
| Prompt types | Text |
| Negative prompts | No |
| Max outputs | 1 |
| Local deployment | Yes |
| VRAM | 80–160 GB |
| System RAM | 96–192 GB |
| API access | Yes |
| Pricing | Free weights |
| Confidence | High |
| Vendor country | China |
| Vendor type | Open lab |
Pricing & hardware
Free weights
This model can be self-hosted or run locally. Approximate GPU memory: 80–160 GB. Approximate system RAM: 96–192 GB. API access is available.