LLM EXPLORER
 LLM Explorer: A Curated Large Language Model Directory and Analytics
Dark Theme
  Agents   Benchmarks   LLM  List    LLM Hosting    LLM Leaderboards    Blog    Newsfeed    Advertise

Qwen 72B by Qwen

 »  All LLMs  »  Qwen  »  Qwen 72B   URL Share it on

  1845   

Qwen 72B is an open-source language model by Qwen. Features: 72b LLM, VRAM: 67.1GB, Context: 32K, License: other, LLM Explorer Score: 0.14, Arc: 65.2, HellaSwag: 85.9, MMLU: 77.4, GSM8K: 70.4.

  Arxiv:2309.16609   Custom code   En   Qwen   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen-72B 

Qwen 72B Benchmarks

ARC: 65.19 vs 96.7 (so35)-32.6%
HellaSwag: 85.94 vs 95.3 (gpt4)-9.8%
MMLU: 77.37 vs 88.3 (so35)-12.4%
GSM8K: 70.43 vs 96.4 (so35)-26.9%
LLME Score: 0.14367
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen 72B (Qwen/Qwen-72B)
🌟 Advertise your project 🚀

Qwen 72B Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Additional Notes 
Model includes a comprehensive 150,000-token vocabulary optimized for multi-languages.
Supported Languages 
zh (high), en (high), multilingual (medium)
Training Details 
Data Sources:
web texts, books, codes
Data Volume:
over 3 trillion tokens
Context Length:
32768
Model Architecture:
Transformer-based
Input Output 
Input Format:
Standard transformer inputs
Accepted Modalities:
text
Output Format:
Textual generation
Performance Tips:
Installation of optional flash-attention for increased efficiency and reduced memory.
LLM NameQwen 72B
Repository 🤗https://huggingface.co/Qwen/Qwen-72B 
Model Size72b
Required VRAM67.1 GB
Updated2026-05-08
MaintainerQwen
Model Typeqwen
Model Files  2.5 GB: 1-of-82   1.7 GB: 2-of-82   1.7 GB: 3-of-82   1.7 GB: 4-of-82   1.7 GB: 5-of-82   1.7 GB: 6-of-82   1.7 GB: 7-of-82   1.7 GB: 8-of-82   1.7 GB: 9-of-82   1.7 GB: 10-of-82   1.7 GB: 11-of-82   1.7 GB: 12-of-82   1.7 GB: 13-of-82   1.7 GB: 14-of-82   1.7 GB: 15-of-82   1.7 GB: 16-of-82   1.7 GB: 17-of-82   1.7 GB: 18-of-82   1.7 GB: 19-of-82   1.7 GB: 20-of-82   1.7 GB: 21-of-82   1.7 GB: 22-of-82   1.7 GB: 23-of-82   1.7 GB: 24-of-82   1.7 GB: 25-of-82   1.7 GB: 26-of-82   1.7 GB: 27-of-82   1.7 GB: 28-of-82   1.7 GB: 29-of-82   1.7 GB: 30-of-82   1.7 GB: 31-of-82   1.7 GB: 32-of-82   1.7 GB: 33-of-82   1.7 GB: 34-of-82   1.7 GB: 35-of-82   1.7 GB: 36-of-82   1.7 GB: 37-of-82   1.7 GB: 38-of-82   1.7 GB: 39-of-82
Supported Languageszh en
Model ArchitectureQWenLMHeadModel
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.32.0
Tokenizer ClassQWenTokenizer
Vocabulary Size152064

Best Alternatives to Qwen 72B

Best Alternatives
Context / RAM
Downloads
Likes
Qwen 72B Chat Int432K / 40.8 GB166047
Qwen 72B Chat32K / 67.1 GB229156
Qwen 72B Chat Int832K / 77 GB11017

Rank the Qwen 72B Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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  

What open-source LLMs or SLMs are you in search of? 53999 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer