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

Qwen2.5 3B Instruct AWQ by Qwen

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

  64685   

Qwen2.5 3B Instruct AWQ is an open-source language model by Qwen. Features: 3b LLM, VRAM: 2.7GB, Context: 32K, License: other, Quantized, Instruction-Based, LLM Explorer Score: 0.21.

  Arxiv:2407.10671   4-bit   Awq Base model:quantized:qwen/qwen... Base model:qwen/qwen2.5-3b-ins...   Chat   Conversational   En   Endpoints compatible   Instruct   Quantized   Qwen2   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-AWQ 

Qwen2.5 3B Instruct AWQ Benchmarks

LLME Score: 0.20716
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 AWQ (Qwen/Qwen2.5-3B-Instruct-AWQ)

Qwen2.5 3B Instruct AWQ Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
Multilingual support, long-context support up to 128K tokens and can generate up to 8K tokens, more resilient to the diversity of system prompts.
Supported Languages 
en (Multilingual support for over 29 languages, including Chinese, English, French, Spanish, Portuguese, German, Italian, Russian, Japanese, Korean, Vietnamese, Thai, Arabic, and more.)
Training Details 
Methodology:
Pretraining & Post-training
Context Length:
32768
Model Architecture:
Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
LLM NameQwen2.5 3B Instruct AWQ
Repository 🤗https://huggingface.co/Qwen/Qwen2.5-3B-Instruct-AWQ 
Base Model(s)  Qwen/Qwen2.5-3B-Instruct   Qwen/Qwen2.5-3B-Instruct
Model Size3b
Required VRAM2.7 GB
Updated2026-07-23
MaintainerQwen
Model Typeqwen2
Instruction-BasedYes
Model Files  2.7 GB
Supported Languagesen
AWQ QuantizationYes
Quantization Typeawq
Model ArchitectureQwen2ForCausalLM
Licenseother
Context Length32768
Model Max Length32768
Transformers Version4.41.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Torch Data Typefloat16
Errorsreplace

Quantized Models of the Qwen2.5 3B Instruct AWQ

Model
Likes
Downloads
VRAM
RuQwen2.5 3B Instruct AWQ5131 GB

Best Alternatives to Qwen2.5 3B Instruct AWQ

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2.5 Coder 3B Instruct AWQ32K / 2.7 GB392358
VibeThinker 3B 8bit128K / 3.3 GB11073
Qwen2.5 3B Legal Id Sft32K / 6.2 GB11060
Akmal Legal Model Sft32K / 6.2 GB1470
... Slm Finetuned Ratu Chairunisa32K / 6.2 GB790
Qwen2.5 3B Legal Sft32K / 6.2 GB2690
Legal Model Sft32K / 6.2 GB1350
Qwen2.5 3B Legal Id Sft32K / 6.2 GB810
...5 3B Instruct Indonesian QLoRA32K / 6.2 GB1510
Qwen Legal Indo Sft32K / 6.2 GB740
Note: green Score (e.g. "73.2") means that the model is better than Qwen/Qwen2.5-3B-Instruct-AWQ.

Rank the Qwen2.5 3B Instruct AWQ 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? 55556 in total.

Email us: info@extractum.io. Our Privacy Policy  | Terms and Conditions  | Suggest an improvement.
Our Social Media →  
Original data from HuggingFace, Arena and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a
  Support LLM Explorer