What are the hardware requirements for Glm 4 9B Chat 1M?

Glm 4 9B Chat 1M requires approximately 18.7 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Glm 4 9B Chat 1M and how large is it?

Glm 4 9B Chat 1M is developed by THUDM, 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 Glm 4 9B Chat 1M?

Glm 4 9B Chat 1M is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Glm 4 9B Chat 1M by THUDM — VRAM 18.7GB

Name: Glm 4 9B Chat 1M
Author: THUDM

Glm 4 9B Chat 1M is an open-source language model by THUDM. Features: 9b LLM, VRAM: 18.7GB, License: other, LLM Explorer Score: 0.19.

Arxiv:2406.12793 Chatglm Custom code En Glm Region:us Safetensors Sharded Tensorflow Thudm Zh

Model Card on HF 🤗: https://huggingface.co/THUDM/glm-4-9b-chat-1m

Glm 4 9B Chat 1M Parameters and Internals

Model Type

text generation, multimodal

Use Cases

Areas:

research, commercial applications, multilingual applications

Primary Use Cases:

multilingual dialogue, long text reasoning (supporting up to 128K context), web browsing, code execution, custom tool calling

Supported Languages

zh (Chinese), en (English), ja (Japanese), ko (Korean), de (German), others (26 languages in total)

Training Details

Methodology:

Pre-trained with data over various domains including semantic, mathematical, reasoning, code, and knowledge datasets. Enhanced with human preference alignment techniques.

Context Length:

131072

Input Output

Input Format:

Chat templates with roles and content

Release Notes

Version:

2024/08/12

Notes:

Code updated with `transformers>=4.44.0`.

Version:

2024/07/24

Notes:

Published latest tech insights related to long text on [Medium](https://medium.com/@ChatGLM/glm-long-scaling-pre-trained-model-contexts-to-millions-caa3c48dea85)

LLM Name	Glm 4 9B Chat 1M
Repository 🤗	https://huggingface.co/THUDM/glm-4-9b-chat-1m
Model Size	9b
Required VRAM	18.7 GB
Updated	2025-07-28
Maintainer	THUDM
Model Type	chatglm
Model Files	1.9 GB: 1-of-10 1.8 GB: 2-of-10 2.0 GB: 3-of-10 1.9 GB: 4-of-10 1.8 GB: 5-of-10 2.0 GB: 6-of-10 1.9 GB: 7-of-10 1.8 GB: 8-of-10 2.0 GB: 9-of-10 1.6 GB: 10-of-10
Supported Languages	zh en
Model Architecture	ChatGLMModel
License	other
Model Max Length	1024000
Transformers Version	4.44.0
Tokenizer Class	ChatGLM4Tokenizer
Padding Token	<\|endoftext\|>
Torch Data Type	bfloat16

Rank the Glm 4 9B Chat 1M 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 9B Chat 1M

Best Alternatives	Context / RAM	Downloads	Likes
Glm 4 9B Chat	0K / 18.7 GB	94984	683
Glm 4 9B Chat	0K / 18.7 GB	82921	708
Glm 4 9B	0K / 18.7 GB	4769	138
Glm 4v 9B	0K / 27.9 GB	92253	268
Codegeex4 All 9B	0K / 18.8 GB	8919	272
Glm 4 9B Chat 1M	0K / 18.7 GB	16201	201
Glm 4 9B	0K / 18.7 GB	13183	144
Codegeex4 All 9B	0K / 18.8 GB	661	253
LongCite Glm4 9B	0K / 20.9 GB	119	34
LongCite Glm4 9B	0K / 20.9 GB	92	32

Note: green Score (e.g. "73.2") means that the model is better than THUDM/glm-4-9b-chat-1m.