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 by unsloth

 »  All LLMs  »  unsloth  »  Qwen2.5 3B Instruct   URL Share it on

  82602   
  Arxiv:2407.10671   Autotrain compatible Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-3b-ins...   Conversational   En   Endpoints compatible   Instruct   Qwen   Qwen2   Region:us   Safetensors   Sharded   Tensorflow   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-3B-Instruct 

Qwen2.5 3B Instruct Benchmarks

LLME Score: 0.27386
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 (unsloth/Qwen2.5-3B-Instruct)
🌟 Advertise your project 🚀

Qwen2.5 3B Instruct Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
Qwen2.5 series includes improvements in knowledge, instruction following, and multilingual support across 29 languages. It features long-context support up to 128K tokens for generating up to 8K tokens. The architecture utilizes RoPE, SwiGLU, RMSNorm, and tied word embeddings.
Supported Languages 
en (native proficiency), zh (native proficiency), fr (native proficiency), es (native proficiency), pt (native proficiency), de (native proficiency), it (native proficiency), ru (native proficiency), ja (native proficiency), ko (native proficiency), vi (native proficiency), th (native proficiency), ar (native proficiency)
Training Details 
Context Length:
32768
Model Architecture:
Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
Input Output 
Accepted Modalities:
text
LLM NameQwen2.5 3B Instruct
Repository 🤗https://huggingface.co/unsloth/Qwen2.5-3B-Instruct 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM6.2 GB
Updated2025-07-08
Maintainerunsloth
Model Typeqwen2
Instruction-BasedYes
Model Files  4.0 GB: 1-of-2   2.2 GB: 2-of-2
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.49.0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 3B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Saba2 3B128K / 6.2 GB160
Tessa T1 3B117K / 6.2 GB203
UIGEN T1.5 3B117K / 6.2 GB121
Qwen2.5 3B Instruct32K / 6.2 GB2040888270
SmallThinker 3B Preview32K / 6.8 GB46018405
Calme 3.2 Baguette 3B32K / 11 GB38381
Calme 3.1 Baguette 3B32K / 6.2 GB38181
Calme 3.2 Instruct 3B32K / 11 GB38373
Chirp 0132K / 6.2 GB1814
Qwen2.5 3B Model Stock V3.132K / 6.8 GB403
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-3B-Instruct.

Rank the Qwen2.5 3B Instruct 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? 49452 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