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 Chat Int8 by Qwen

 »  All LLMs  »  Qwen  »  Qwen 72B Chat Int8   URL Share it on

  110   

Qwen 72B Chat Int8 is an open-source language model by Qwen. Features: 72b LLM, VRAM: 77GB, Context: 32K, License: other, LLM Explorer Score: 0.11.

  Arxiv:2009.03300   Arxiv:2305.08322   Arxiv:2307.11088   Arxiv:2309.16609   8-bit   Custom code   En   Gptq   Qwen   Region:us   Safetensors   Sharded   Tensorflow   Zh
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen-72B-Chat-Int8 

Qwen 72B Chat Int8 Benchmarks

LLME Score: 0.10583
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen 72B Chat Int8 (Qwen/Qwen-72B-Chat-Int8)
🌟 Advertise your project 🚀

Qwen 72B Chat Int8 Parameters and Internals

Model Type 
text generation
Use Cases 
Areas:
research, commercial applications
Applications:
AI assistant
Primary Use Cases:
Long-context understanding, Text generation
Additional Notes 
Quantized Int8 model for reduced resource usage.
Supported Languages 
Chinese (high), English (high), Multilingual (medium), Code (medium), Math (medium)
Training Details 
Data Sources:
web texts, books, codes
Data Volume:
3 trillion tokens
Methodology:
Transformer-based, alignment techniques
Context Length:
32768
Model Architecture:
80 layers, 64 heads, d_model 8192, vocab size 151851
Input Output 
Input Format:
Text input
Accepted Modalities:
Text
Output Format:
Text output
LLM NameQwen 72B Chat Int8
Repository 🤗https://huggingface.co/Qwen/Qwen-72B-Chat-Int8 
Model Size72b
Required VRAM77 GB
Updated2026-05-26
MaintainerQwen
Model Typeqwen
Model Files  2.5 GB: 1-of-39   2.0 GB: 2-of-39   1.9 GB: 3-of-39   2.0 GB: 4-of-39   2.0 GB: 5-of-39   2.0 GB: 6-of-39   2.0 GB: 7-of-39   1.9 GB: 8-of-39   2.0 GB: 9-of-39   2.0 GB: 10-of-39   2.0 GB: 11-of-39   2.0 GB: 12-of-39   1.9 GB: 13-of-39   2.0 GB: 14-of-39   2.0 GB: 15-of-39   2.0 GB: 16-of-39   2.0 GB: 17-of-39   1.9 GB: 18-of-39   2.0 GB: 19-of-39   2.0 GB: 20-of-39   2.0 GB: 21-of-39   2.0 GB: 22-of-39   1.9 GB: 23-of-39   2.0 GB: 24-of-39   2.0 GB: 25-of-39   2.0 GB: 26-of-39   2.0 GB: 27-of-39   1.9 GB: 28-of-39   2.0 GB: 29-of-39   2.0 GB: 30-of-39   2.0 GB: 31-of-39   2.0 GB: 32-of-39   1.9 GB: 33-of-39   2.0 GB: 34-of-39   2.0 GB: 35-of-39   2.0 GB: 36-of-39   2.0 GB: 37-of-39   0.7 GB: 38-of-39   2.5 GB: 39-of-39
Supported Languageszh en
Model ArchitectureQWenLMHeadModel
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.32.0
Tokenizer ClassQWenTokenizer
Vocabulary Size152064

Best Alternatives to Qwen 72B Chat Int8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen 72B32K / 67.1 GB1845362
Qwen 72B Chat Int432K / 40.8 GB166047
Qwen 72B Chat32K / 67.1 GB229156
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen-72B-Chat-Int8.

Rank the Qwen 72B Chat Int8 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