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.
PUBLISHED2025-08-10
OBSERVED2026-08-11
AGE1y
SOURCES1
- 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
COMMUNITY
No curated reactions recorded for this event. Facts and takes are kept in separate layers — community context is added by hand, never blended into the record above.