What are the hardware requirements for Graph R1 7B?

Graph R1 7B requires approximately 15.3 GB of VRAM and supports a context window of 986K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Graph R1 7B and how large is it?

Graph R1 7B is developed by HKUST-DSAIL, a model with 7b 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 Graph R1 7B?

Graph R1 7B is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Graph R1 7B by HKUST-DSAIL — VRAM 15.3GB, 986K context

Name: Graph R1 7B
Author: HKUST-DSAIL

Graph R1 7B is an open-source language model by HKUST-DSAIL. Features: 7b LLM, VRAM: 15.3GB, Context: 986K, License: mit, Instruction-Based, LLM Explorer Score: 0.19.

Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-7b-ins... Instruct Qwen2 Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/HKUST-DSAIL/Graph-R1-7B

Graph R1 7B Parameters and Internals

LLM Name	Graph R1 7B
Repository 🤗	https://huggingface.co/HKUST-DSAIL/Graph-R1-7B
Base Model(s)	Qwen/Qwen2.5-7B-Instruct-1M Qwen/Qwen2.5-7B-Instruct-1M
Model Size	7b
Required VRAM	15.3 GB
Updated	2026-07-24
Maintainer	HKUST-DSAIL
Model Type	qwen2
Instruction-Based	Yes
Model Files	5.0 GB: 1-of-4 5.0 GB: 2-of-4 5.0 GB: 3-of-4 0.3 GB: 4-of-4
Model Architecture	Qwen2ForCausalLM
License	mit
Context Length	1010000
Model Max Length	1010000
Transformers Version	4.51.3
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	152064
Torch Data Type	bfloat16
Errors	replace

Rank the Graph R1 7B 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 Graph R1 7B

Best Alternatives	Context / RAM	Downloads	Likes
Qwen2.5 7B Instruct 1M	986K / 15.4 GB	52534	373
Rewnozom	986K / 30.5 GB	742	1
Hush Qwen2.5 7B RP V1.4 1M	986K / 15.2 GB	10	2
Qwen2.5 7B RRP 1M	986K / 15.2 GB	5	6
Qwen2.5 7B CelestialHarmony 1M	986K / 14.8 GB	8	7
Q2.5 Instruct 1M Harmony	986K / 15.2 GB	4	2
Impish QWEN 7B 1M	986K / 15.2 GB	4	6
COCO 7B Instruct 1M	986K / 15.2 GB	9	4
Apollo 7B	986K / 15.2 GB	8	0
Qwen2.5 7B Sky R1 Mini	986K / 15.2 GB	6	0

Note: green Score (e.g. "73.2") means that the model is better than HKUST-DSAIL/Graph-R1-7B.