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

Qwen2 7B Instruct GPTQ Int8 by Qwen

 »  All LLMs  »  Qwen  »  Qwen2 7B Instruct GPTQ Int8   URL Share it on

  266   
  Arxiv:2309.00071   8-bit   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2-7b-instr...   Chat   Conversational   En   Endpoints compatible   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2-7B-Instruct-GPTQ-Int8 

Qwen2 7B Instruct GPTQ Int8 Benchmarks

LLME Score: 0.19809
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2 7B Instruct GPTQ Int8 (Qwen/Qwen2-7B-Instruct-GPTQ-Int8)

Qwen2 7B Instruct GPTQ Int8 Parameters and Internals

Model Type 
text-generation
Use Cases 
Areas:
research, commercial applications
Limitations:
Potential performance impact on shorter texts when using long-context capabilities.
Additional Notes 
Quantized models compared in terms of performance and speed, like GPTQ-Int8.
Supported Languages 
en (Supported)
Training Details 
Methodology:
Pretrained with a large amount of data and post-trained with supervised finetuning and direct preference optimization.
Context Length:
131072
Model Architecture:
Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc.
Input Output 
Input Format:
Supports a context length of up to 131,072 tokens using techniques like YARN.
Accepted Modalities:
text
Performance Tips:
Install transformers>=4.37.0 and consider deploying using vLLM for better performance on long texts.
LLM NameQwen2 7B Instruct GPTQ Int8
Repository 🤗https://huggingface.co/Qwen/Qwen2-7B-Instruct-GPTQ-Int8 
Base Model(s)  Qwen2 7B Instruct   Qwen/Qwen2-7B-Instruct
Model Size7b
Required VRAM8.9 GB
Updated2025-03-18
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-3   3.8 GB: 2-of-3   1.1 GB: 3-of-3
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.38.2
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size152064
Torch Data Typefloat16
Errorsreplace

Quantized Models of the Qwen2 7B Instruct GPTQ Int8

Model
Likes
Downloads
VRAM
Term Qwen2 7 Json Lora050 GB

Best Alternatives to Qwen2 7B Instruct GPTQ Int8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 7B Instruct GPTQ Int432K / 5.6 GB5226919
....5 Coder 7B Instruct GPTQ Int432K / 5.6 GB358666
Qwen2.5 7B Instruct GPTQ Int832K / 8.9 GB2470614
....5 Coder 7B Instruct GPTQ Int832K / 8.9 GB262654
Qwen2 7B Instruct GPTQ Int432K / 5.6 GB229125
...B Instruct 1M Unsloth Bnb 4bit986K / 7.5 GB17442
Qwen2.5 7B Instruct 1M 4bit986K / 4.3 GB7107
Qwen2.5 7B Instruct 1M 8bit986K / 8.1 GB2393
Qwen2.5 7B Instruct 1M 6bit986K / 6.2 GB1212
Kyro N1 7B32K / 15.2 GB3626
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2-7B-Instruct-GPTQ-Int8.

Rank the Qwen2 7B Instruct GPTQ 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? 45269 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.
Release v20241227
  Support LLM Explorer