MODEL REFERENCE / zai-org

zai-org/Glyph

Visual-text compression framework that renders long text into images and processes them with a reasoning VLM, scaling effective context length

Reasoning multimodal model for visual-text compression, single-GPU deployable

vLLMdense10B131,072 ctxvLLM 0.11.0+multimodal

02 / Configure

Configure serving

Choose engine, hardware and deployment options. The command updates as you go.

03 / Understand

Model notes and examples