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

Qwen2.5 3B Instruct GPTQ Int8 by Qwen

 »  All LLMs  »  Qwen  »  Qwen2.5 3B Instruct GPTQ Int8   URL Share it on

  1396   
  Arxiv:2407.10671   8-bit   Autotrain compatible Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-3b-ins...   Chat   Conversational   En   Endpoints compatible   Gptq   Instruct   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8 

Qwen2.5 3B Instruct GPTQ Int8 Benchmarks

LLME Score: 0.19935
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 3B Instruct GPTQ Int8 (Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8)
🌟 Advertise your project 🚀

Qwen2.5 3B Instruct GPTQ Int8 Parameters and Internals

Model Type 
Causal Language Model
Use Cases 
Areas:
Research, Commercial applications
Applications:
Coding, Mathematics assistance, Text generation
Primary Use Cases:
Instruction following, Generating long texts, Understanding structured data, Generating structured outputs, Multilingual text generation
Additional Notes 
The model is GPTQ-quantized 8-bit instruction-tuned.
Supported Languages 
English (primary), others (Chinese, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more)
Training Details 
Data Sources:
Qwen specialized expert models
Methodology:
Pretraining & Post-training with expert models in domains like coding and mathematics
Context Length:
32768
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
Input Output 
Accepted Modalities:
text
Performance Tips:
Use the latest version of transformers to avoid KeyError
LLM NameQwen2.5 3B Instruct GPTQ Int8
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM3.5 GB
Updated2025-09-23
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  3.5 GB
Supported Languagesen
GPTQ QuantizationYes
Quantization Typegptq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.39.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Best Alternatives to Qwen2.5 3B Instruct GPTQ Int8

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 3B Instruct GPTQ Int432K / 2.1 GB11933
TethysAI Base Reasoning32K / 6.2 GB550
...5 3B Instruct Unsloth Bnb 4bit32K / 2.4 GB471957
Kyro N1 3B32K / 6.2 GB1212
Athena 1 3B32K / 6.2 GB31
Qwen2.5 3B Reasoner32K / 6.2 GB60
...2.5 Coder 3B Instruct Bnb 4bit32K / 2 GB760794
QwQ LCoT 3B Instruct32K / 6.2 GB95
Test StealthThinker32K / 6.2 GB60
Qwen2.5 3B Instruct Chat Sft32K / 6.2 GB50
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-3B-Instruct-GPTQ-Int8.

Rank the Qwen2.5 3B 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? 51544 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 v20241124
  Support LLM Explorer