What are the hardware requirements for GLM Z1 32B 0414?

GLM Z1 32B 0414 requires approximately 65.7 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed GLM Z1 32B 0414 and how large is it?

GLM Z1 32B 0414 is developed by THUDM, a model with 32b 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 Z1 32B 0414?

GLM Z1 32B 0414 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

GLM Z1 32B 0414 by THUDM — VRAM 65.7GB, 32K context

Name: GLM Z1 32B 0414
Author: THUDM

GLM Z1 32B 0414 is an open-source language model by THUDM. Features: 32b LLM, VRAM: 65.7GB, Context: 32K, License: mit, LLM Explorer Score: 0.21.

Arxiv:2406.12793 Autotrain compatible Conversational En Endpoints compatible Glm4 Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/THUDM/GLM-Z1-32B-0414

GLM Z1 32B 0414 Parameters and Internals

LLM Name	GLM Z1 32B 0414
Repository 🤗	https://huggingface.co/THUDM/GLM-Z1-32B-0414
Model Size	32b
Required VRAM	65.7 GB
Updated	2025-07-28
Maintainer	THUDM
Model Type	glm4
Model Files	5.0 GB: 1-of-14 5.0 GB: 2-of-14 4.8 GB: 3-of-14 4.5 GB: 4-of-14 5.0 GB: 5-of-14 5.0 GB: 6-of-14 4.8 GB: 7-of-14 4.5 GB: 8-of-14 5.0 GB: 9-of-14 5.0 GB: 10-of-14 4.8 GB: 11-of-14 4.5 GB: 12-of-14 5.0 GB: 13-of-14 2.8 GB: 14-of-14
Supported Languages	zh en
Model Architecture	Glm4ForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.52.0.dev0
Tokenizer Class	PreTrainedTokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151552
Torch Data Type	bfloat16

Rank the GLM Z1 32B 0414 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

Quantized Models of the GLM Z1 32B 0414

Model	Likes	Downloads	VRAM
GLM Z1 32B 0414 4bit	2	61	18 GB

Best Alternatives to GLM Z1 32B 0414

Best Alternatives	Context / RAM	Downloads	Likes
GLM Z1 Rumination 32B 0414	128K / 66.4 GB	1147	110
GLM Z1 Rumination 32B 0414	128K / 66.4 GB	235	118
GLM 4 32B 0414	32K / 65.7 GB	222429	459
GLM 4 32B 0414	32K / 65.7 GB	11900	487
GLM Z1 32B 0414 Heretic V1	32K / 65.2 GB	5	0
GLM Z1 32B 0414	32K / 65.7 GB	7993	196
Austral 32B GLM4 Winton	32K / 65.7 GB	66	9
GLM 4 32B Base 0414	32K / 65.7 GB	925	28
GLM 4 32B Base 0414	32K / 65.7 GB	805	37
GLM 4 32B Base 32K	32K / 65.4 GB	16	38

Note: green Score (e.g. "73.2") means that the model is better than THUDM/GLM-Z1-32B-0414.