What are the hardware requirements for GLM 4.5 Base?

GLM 4.5 Base requires approximately 250.7 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM 4.5 Base and how large is it?

GLM 4.5 Base is developed by zai-org, a model with 358.3b 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 GLM 4.5 Base?

GLM 4.5 Base is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM 4.5 Base by zai-org — VRAM 250.7GB, 128K context

Name: GLM 4.5 Base
Author: zai-org

GLM 4.5 Base is an open-source language model by zai-org. Features: 358.3b LLM, VRAM: 250.7GB, Context: 128K, License: mit, LLM Explorer Score: 0.21.

Arxiv:2508.06471 En Endpoints compatible Glm4 moe Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/zai-org/GLM-4.5-Base

GLM 4.5 Base Parameters and Internals

LLM Name	GLM 4.5 Base
Repository 🤗	https://huggingface.co/zai-org/GLM-4.5-Base
Model Size	358.3b
Required VRAM	250.7 GB
Updated	2026-08-04
Maintainer	zai-org
Model Type	glm4_moe
Model Files	5.3 GB: 1-of-134 5.4 GB: 2-of-134 5.3 GB: 3-of-134 5.3 GB: 4-of-134 5.4 GB: 5-of-134 5.3 GB: 6-of-134 5.3 GB: 7-of-134 5.4 GB: 8-of-134 5.3 GB: 9-of-134 5.3 GB: 10-of-134 5.4 GB: 11-of-134 5.3 GB: 12-of-134 5.3 GB: 13-of-134 5.4 GB: 14-of-134 5.3 GB: 15-of-134 5.3 GB: 16-of-134 5.4 GB: 17-of-134 5.3 GB: 18-of-134 5.3 GB: 19-of-134 5.3 GB: 20-of-134 5.4 GB: 21-of-134 5.3 GB: 22-of-134 5.3 GB: 23-of-134 5.4 GB: 24-of-134 5.3 GB: 25-of-134 5.3 GB: 26-of-134 5.4 GB: 27-of-134 5.3 GB: 28-of-134 5.3 GB: 29-of-134 5.4 GB: 30-of-134 5.3 GB: 31-of-134 5.3 GB: 32-of-134 5.4 GB: 33-of-134 5.3 GB: 34-of-134 5.3 GB: 35-of-134 5.4 GB: 36-of-134 5.3 GB: 37-of-134 5.3 GB: 38-of-134 5.4 GB: 39-of-134 5.3 GB: 40-of-134 5.3 GB: 41-of-134 5.4 GB: 42-of-134 5.3 GB: 43-of-134 5.3 GB: 44-of-134 5.4 GB: 45-of-134 5.4 GB: 46-of-134 5.3 GB: 47-of-134
Supported Languages	en zh
Model Architecture	Glm4MoeForCausalLM
License	mit
Context Length	131072
Model Max Length	131072
Transformers Version	4.54.0
Vocabulary Size	151552
Torch Data Type	bfloat16

Rank the GLM 4.5 Base 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 GLM 4.5 Base

Best Alternatives	Context / RAM	Downloads	Likes
GLM 4.7	198K / 327.5 GB	64576	2047
GLM 4.7	198K / 335.4 GB	18	10
GLM 4.5	128K / 337 GB	160781	1403
GLM 4.5	128K / 337 GB	17	7

Note: green Score (e.g. "73.2") means that the model is better than zai-org/GLM-4.5-Base.