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 0.5B Instruct by unsloth

 »  All LLMs  »  unsloth  »  Qwen2.5 0.5B Instruct   URL Share it on

  130065   

Qwen2.5 0.5B Instruct is an open-source language model by unsloth. Features: 0.5b LLM, VRAM: 1GB, Context: 32K, License: apache-2.0, Instruction-Based, LLM Explorer Score: 0.22.

  Arxiv:2407.10671 Base model:finetune:qwen/qwen2... Base model:qwen/qwen2.5-0.5b-i...   Conversational   Deploy:azure   En   Endpoints compatible   Instruct   Qwen2   Region:us   Safetensors   Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct 

Qwen2.5 0.5B Instruct Benchmarks

LLME Score: 0.22417
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen2.5 0.5B Instruct (unsloth/Qwen2.5-0.5B-Instruct)
🌟 Advertise your project 🚀

Qwen2.5 0.5B Instruct Parameters and Internals

Model Type 
Causal Language Models
Additional Notes 
Significant improvements in knowledge, coding, mathematics, and instruction following abilities. Multilingual support for more than 29 languages. Long-context support up to 128K tokens, generating up to 8K tokens. Robust against diverse system prompts, enhancing chatbot capabilities.
Supported Languages 
English (Fluent), Chinese (Fluent), French (Fluent), Spanish (Fluent), Portuguese (Fluent), German (Fluent), Italian (Fluent), Russian (Fluent), Japanese (Fluent), Korean (Fluent), Vietnamese (Fluent), Thai (Fluent), Arabic (Fluent)
Training Details 
Context Length:
32768
Model Architecture:
Transformers with RoPE, SwiGLU, RMSNorm, Attention QKV bias and tied word embeddings
Input Output 
Input Format:
Structured input using predefined roles in JSON format
Accepted Modalities:
text
Output Format:
JSON
LLM NameQwen2.5 0.5B Instruct
Repository 🤗https://huggingface.co/unsloth/Qwen2.5-0.5B-Instruct 
Base Model(s)  Qwen/Qwen2.5-0.5B-Instruct   Qwen/Qwen2.5-0.5B-Instruct
Model Size0.5b
Required VRAM1 GB
Updated2026-05-13
Maintainerunsloth
Model Typeqwen2
Instruction-BasedYes
Model Files  1.0 GB
Supported Languagesen
Model ArchitectureQwen2ForCausalLM
Licenseapache-2.0
Context Length32768
Model Max Length32768
Transformers Version4.49.0.dev0
Tokenizer ClassQwen2Tokenizer
Padding Token<|vision_pad|>
Vocabulary Size151936
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen2.5 0.5B Instruct

Best Alternatives
Context / RAM
Downloads
Likes
Qwen2 0.5B Abyme Merge3128K / 1.3 GB231
Qwen2 0.5B Abyme Merge2128K / 0.3 GB220
Qwen2.5 0.5B Instruct64K / 1 GB70
Qwen2.5 0.5B Instruct32K / 1 GB6089483505
...5 0.5B Instruct Abliterated Ru32K / 2 GB4320
Q SS 0.5B Reasoning Math32K / 1 GB592
BoyBarley Sparky V332K / 1 GB2250
Qwen2 0.5B Instruct32K / 1 GB1440477200
DAC5.4 0.5B32K / 1 GB340
...ext Aware Abstention Qwen 0.5B32K / 2 GB480
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Qwen2.5-0.5B-Instruct.

Rank the Qwen2.5 0.5B 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? 53999 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