Skip to content

EthenEthenEthen

LoginPlatformTry Ethen

Open Source Model Profile · zai-org

GLM-4.6V-Flash

GLM-4.6V-Flash is a 10.29B-parameter glm4v vision-language release from zai-org. According to the model card, the Flash variant targets local deployment and low-latency applications.

Publisher
zai-org
Task
image-text-to-text
Model type
glm4v
License
mit
Library
transformers
Publication status
Approved for indexing

Model overview

GLM-4.6V-Flash is published by zai-org as a glm4v image-text-to-text model. The captured configuration identifies Glm4vForConditionalGeneration with model type glm4v, and Safetensors metadata reports 10,292,777,472 parameters. According to the model card, it is the lightweight GLM-4.6V-series variant for local deployment and low-latency use.

Recorded capabilities

Flash lightweight variant

According to the model card, GLM-4.6V-Flash is the lightweight model in the GLM-4.6V series, optimized for local deployment and low-latency applications.

10.29B GLM4V weights

Captured configuration identifies Glm4vForConditionalGeneration with model type glm4v, and Safetensors metadata reports 10,292,777,472 parameters.

Native multimodal function calling

According to the model card, the series integrates native function calling that uses images, screenshots, and document pages directly as tool inputs.

128K training context

According to the model card, GLM-4.6V scales its context window to 128K tokens in training, with documented vLLM and SGLang inference settings.

Use cases in the source record

  • Vision-language work, including image-grounded conversational use, with the publisher-described lightweight Flash variant for local or low-latency settings.
  • Vision-driven tool-use experiments using the model card's native multimodal function-calling description and AutoProcessor loading pattern.

Limitations and unknowns

  • No Ethen-measured evaluation results were extracted from this record.
  • Provider state is historical snapshot data and should be refreshed before being presented as current.
  • Series, performance, and capability claims are publisher model-card statements and were not independently verified by Ethen.

Source and provenance

Source: zai-org/GLM-4.6V-Flash

Captured: Unknown. Processed: 2026-09-07T19:35:01.508102+00:00.

GLM-4.6V This model is part of the GLM-V family of models, introduced in the paper GLM-4.1V-Thinking and GLM-4.5V: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning . GLM-4.6V Blog : https://z.ai/blog/glm-4.6v Paper : https://huggingface.co/papers/2507.01006 GitHub Repository : https://github.com/zai-org/GLM-V Online Demo : https://chat.z.ai/ API Access : Z.ai Open Platform Desktop Assistant App : https://huggingface.co/spaces/zai-org/GLM-4.5V-Demo-App Introduction GLM-4.6V series model includes two versions: GLM-4.6V (106B), a foundation model designed for cloud and high-performance cluster scenarios, and…

F001F002F003F004F005F006F007F010F011F012F013F014F015F016