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

Qwen2.5 3B by Qwen

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

  487949   

Qwen2.5 3B is an open-source language model by Qwen. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: other, LLM Explorer Score: 0.3.

  Arxiv:2407.10671   Conversational   En   Eval-results   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-3B 

Qwen2.5 3B Benchmarks

LLME Score: 0.30134
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 (Qwen/Qwen2.5-3B)
🌟 Advertise your project 🚀

Qwen2.5 3B Parameters and Internals

Model Type 
Causal Language Model
Additional Notes 
We do not recommend using base language models for conversations; instead, apply post-training like SFT, RLHF, etc.
Supported Languages 
English (proficient), Chinese (proficient), French (proficient), Spanish (proficient), Portuguese (proficient), German (proficient), Italian (proficient), Russian (proficient), Japanese (proficient), Korean (proficient), Vietnamese (proficient), Thai (proficient), Arabic (proficient), Other (proficient in additional languages totaling over 29)
Training Details 
Methodology:
Pretraining
Context Length:
32768
Model Architecture:
transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
LLM NameQwen2.5 3B
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-3B 
Model Size3b
Required VRAM6.2 GB
Updated2026-07-06
MaintainerQwen
Model Typeqwen2
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 Version4.40.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 3B

Model
Likes
Downloads
VRAM
Qwen2.5 3B Instruct Heretic11006 GB
Qwen2.5 3B Bnb 4bit3468812 GB
Qwen2.5 3B Unsloth Bnb 4bit048772 GB
Qwen2.5 3B Instruct 4bit1205911 GB

Best Alternatives to Qwen2.5 3B

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB63449747
VibeThinker 3B128K / 6.2 GB1970
...ibeThinker 3B SFT Fable5 Glint128K / 6.2 GB440
Saba1.5 Pro 3B128K / 5.8 GB101
...b Sft Stage1.2 Ss1 Expert Math128K / 15.1 GB70
...b Sft Stage1.2 Ss1 Expert News128K / 15.1 GB90
...2 Ss1 Expert Fictional Lyrical128K / 15.1 GB50
... Formattedtext Math Wiki Merge128K / 15.1 GB60
...tage1.1 Ss1 With Math.no Issue128K / 15.1 GB70
...ware Howto Formattedtext Merge128K / 15.1 GB60
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-3B.

Rank the Qwen2.5 3B 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? 54931 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