What are the hardware requirements for LongReward Glm4 9B DPO?

LongReward Glm4 9B DPO requires approximately 18.8 GB of VRAM and supports a context window of 64K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed LongReward Glm4 9B DPO and how large is it?

LongReward Glm4 9B DPO 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 LongReward Glm4 9B DPO?

LongReward Glm4 9B DPO is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

LongReward Glm4 9B DPO by zai-org — VRAM 18.8GB, 64K context

Name: LongReward Glm4 9B DPO
Author: zai-org

LongReward Glm4 9B DPO is an open-source language model by zai-org. Features: 9b LLM, VRAM: 18.8GB, Context: 64K, License: other, LLM Explorer Score: 0.15.

Arxiv:2410.21252 Base model:finetune:zai-org/gl... Base model:zai-org/glm-4-9b-ch... Chatglm Conversational Dataset:thudm/longreward-10k En Glm Region:us Safetensors Sharded Tensorflow Zh

Model Card on HF 🤗: https://huggingface.co/zai-org/LongReward-glm4-9b-DPO

LongReward Glm4 9B DPO Parameters and Internals

LLM Name	LongReward Glm4 9B DPO
Repository 🤗	https://huggingface.co/zai-org/LongReward-glm4-9b-DPO
Base Model(s)	Glm 4 9B Chat Hf THUDM/glm-4-9b-chat-hf
Model Size	9b
Required VRAM	18.8 GB
Updated	2026-08-08
Maintainer	zai-org
Model Type	glm
Model Files	5.0 GB: 1-of-4 4.9 GB: 2-of-4 4.9 GB: 3-of-4 4.0 GB: 4-of-4
Supported Languages	en zh
Model Architecture	GlmForCausalLM
License	other
Context Length	65536
Model Max Length	65536
Transformers Version	4.46.0.dev0
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<\|endoftext\|>
Vocabulary Size	151552
Torch Data Type	bfloat16

Rank the LongReward Glm4 9B DPO 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 LongReward Glm4 9B DPO

Best Alternatives	Context / RAM	Downloads	Likes
Glm 4 9B Chat 1M Hf	1024K / 19 GB	1114	12
Glm 4 9B Chat 1M Hf	1024K / 19 GB	1862	14
Glm 4 9B Chat Hf	128K / 18.8 GB	5085	14
Glm 4 9B Chat Hf	128K / 18.8 GB	17790	25
Glm 4 9B Hf	8K / 18.8 GB	1588	10
Glm 4 9B Hf	8K / 18.8 GB	853	7

Note: green Score (e.g. "73.2") means that the model is better than zai-org/LongReward-glm4-9b-DPO.