What are the hardware requirements for Glyph?

Glyph requires approximately 20.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Glyph and how large is it?

Glyph is developed by zai-org, a model with 9b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Glyph?

Glyph is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Glyph by zai-org — VRAM 20.6GB

Name: Glyph
Author: zai-org

Glyph is an open-source language model by zai-org. Features: 9b LLM, VRAM: 20.6GB, License: mit, LLM Explorer Score: 0.23.

Arxiv:2510.17800 Base model:finetune:zai-org/gl... Base model:zai-org/glm-4.1v-9b... Conversational Deploy:azure En Endpoints compatible Glm4v Image-text-to-text Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/zai-org/Glyph

Glyph Parameters and Internals

LLM Name	Glyph
Repository 🤗	https://huggingface.co/zai-org/Glyph
Base Model(s)	zai-org/GLM-4.1V-9B-Base zai-org/GLM-4.1V-9B-Base
Model Size	9b
Required VRAM	20.6 GB
Updated	2026-08-08
Maintainer	zai-org
Model Type	glm4v
Model Files	5.3 GB: 1-of-4 5.3 GB: 2-of-4 5.3 GB: 3-of-4 4.7 GB: 4-of-4
Supported Languages	zh en
Model Architecture	Glm4vForConditionalGeneration
License	mit
Model Max Length	128000
Transformers Version	4.57.1
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|endoftext\|>

Rank the Glyph capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Best Alternatives to Glyph

Best Alternatives	Context / RAM	Downloads	Likes
GLM 4.1V 9B Thinking	64K / 20.6 GB	74	2
GLM 4.1V 9B Thinking	0K / 20.6 GB	377189	784
AutoGLM Phone 9B	0K / 20.6 GB	22901	442
AutoGLM Phone 9B Multilingual	0K / 20.6 GB	686	240
UI2Code N	0K / 20.6 GB	338	23
WebVIA Agent	0K / 20.6 GB	153	20
GLM 4.1V 9B Base	0K / 20.6 GB	1636	68
GLM 4.1V 9B Thinking 8bit	0K / 11.7 GB	385	3

Note: green Score (e.g. "73.2") means that the model is better than zai-org/Glyph.