# GLM-4.5V-FP8: quantised vision-language model from Z.ai

> Z.ai published an FP8 quantised version of the GLM-4.5V vision-language model on Hugging Face. The model is a quantised variant of GLM-4.5-Air-Base, supports image-text-to-text tasks, and is conversational in both Chinese and English under an MIT license.

| | |
|---|---|
| **Tool** | Z.ai |
| **Version** | — |
| **Kind** | release |
| **Published** | 2025-08-10 |
| **Observed** | 2026-08-11 |
| **Significance** | 1/5 |
| **Breaking** | no |
| **Categories** | feature, model-support |

> **Note:** this classification is below our confidence threshold and is pending human review.

## What changed


- Pipeline tag: image-text-to-text
- Library: transformers
- Quantised from: zai-org/GLM-4.5-Air-Base
- Tags: glm4v_moe, conversational, zh, en
- Arxiv reference: 2507.01006
- License: MIT
- Endpoints compatible, compressed-tensors


## Sources

- [hf_model](https://huggingface.co/zai-org/GLM-4.5V-FP8) — retrieved 2026-08-11


## Community

_No curated reactions recorded. Facts and community takes are kept in separate layers
and never blended._

---
Canonical: https://changelogs.info/zai/glm-4-5v-fp8-quantised-vision-language-model-from-z-ai
Entity: https://changelogs.info/zai
Event ID: `evt_2025-08-10_zai_zai-org-glm-4-5v-fp8`
Licence: event synthesis © changelogs.info, CC BY 4.0. Linked sources belong to their vendors.