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 Instruct by Qwen

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

  10226936   

Qwen2.5 3B Instruct is an open-source language model by Qwen. Features: 3b LLM, VRAM: 6.2GB, Context: 32K, License: other, Instruction-Based, LLM Explorer Score: 0.39.

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

Qwen2.5 3B Instruct Benchmarks

MMLU Pro: 25.05
GPQA: 3.02
MUSR: 7.57
BBH: 25.8
IFEval: 64.75 vs 88 (so35)-26.4%
MATH Lvl 5: 36.78
LLME Score: 0.39474
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 (Qwen/Qwen2.5-3B-Instruct)
🌟 Advertise your project 🚀

Qwen2.5 3B Instruct Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
Qwen2.5 series offers models from 0.5 to 72 billion parameters, with enhanced capabilities in coding, math, instruction following, and multilingual support.
Supported Languages 
English (Full), Others (Basic)
Training Details 
Methodology:
Pretraining & Post-training with transformers using RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings.
Context Length:
32768
Model Architecture:
Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
LLM NameQwen2.5 3B Instruct
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-3B-Instruct 
Base Model(s)  Qwen/Qwen2.5-3B   Qwen/Qwen2.5-3B
Model Size3b
Required VRAM6.2 GB
Updated2026-04-18
MaintainerQwen
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 Version4.43.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Quantized Models of the Qwen2.5 3B Instruct

Model
Likes
Downloads
VRAM
Coder GRPO 3B726716 GB
...5 3B Instruct Unsloth Bnb 4bit71536722 GB
OpenCogito07796 GB
TethysAI Base Reasoning0556 GB
Kyro N1 3B12126 GB
Athena 1 3B136 GB
QwQ LCoT 3B Instruct5356 GB
Test StealthThinker0326 GB
Qwen2.5 3B Instruct AWQ163282432 GB
Qwen2.5 3B Instruct Bnb 4bit14435192 GB

Best Alternatives to Qwen2.5 3B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Saba2 3B128K / 6.2 GB240
Tessa T1 3B117K / 6.2 GB165
UIGEN T1.5 3B117K / 6.2 GB111
SmallThinker 3B Preview32K / 6.8 GB30529412
FlameDesigner Qwen2.5 3B V132K / 6.2 GB2330
Qwen2.5 Coder 3B Instruct32K / 6.2 GB451109101
Qwen2.5 3B Instruct Heretic32K / 6.2 GB921
Menda 3B 50032K / 6.2 GB150
Menda 3B 75032K / 6.2 GB231
Chirp 0132K / 6.2 GB714

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? 53407 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