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

Qwen 2.5 3B Smarteaz 0.01a by Nexesenex

 »  All LLMs  »  Nexesenex  »  Qwen 2.5 3B Smarteaz 0.01a   URL Share it on

  8   

Qwen 2.5 3B Smarteaz 0.01a is an open-source language model by Nexesenex. Features: 3b LLM, VRAM: 6.3GB, Context: 32K, Instruction-Based, Code Generating, Merged, LLM Explorer Score: 0.23.

  Merged Model   Arxiv:2403.19522 Base model:huihui-ai/qwen2.5-3... Base model:huihui-ai/qwen2.5-c...   Codegen   Conversational   Endpoints compatible   Instruct   Model-index   Qwen2   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a 

Qwen 2.5 3b Smarteaz 0.01a Benchmarks

LLME Score: 0.22586
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Qwen 2.5 3B Smarteaz 0.01a (Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a)

Qwen 2.5 3B Smarteaz 0.01a Parameters and Internals

LLM NameQwen 2.5 3b Smarteaz 0.01a
Repository 🤗https://huggingface.co/Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a 
Base Model(s)  Dria Agent A 3B Abliterated   huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated   huihui-ai/Qwen2.5-3B-Instruct-abliterated   huihui-ai/Dria-Agent-a-3B-abliterated   huihui-ai/Qwen2.5-Coder-3B-Instruct-abliterated   huihui-ai/Qwen2.5-3B-Instruct-abliterated
Merged ModelYes
Model Size3b
Required VRAM6.3 GB
Updated2026-07-01
MaintainerNexesenex
Model Typeqwen2
Instruction-BasedYes
Model Files  1.0 GB: 1-of-7   1.0 GB: 2-of-7   1.0 GB: 3-of-7   1.0 GB: 4-of-7   1.0 GB: 5-of-7   1.0 GB: 6-of-7   0.3 GB: 7-of-7
Generates CodeYes
Model ArchitectureQwen2ForCausalLM
Context Length32768
Model Max Length32768
Transformers Version4.48.3
Tokenizer ClassQwen2Tokenizer
Padding Token<|im_end|>
Vocabulary Size151665
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to Qwen 2.5 3B Smarteaz 0.01a

Best Alternatives
Context / RAM
Downloads
Likes
VibeThinker 3B128K / 6.2 GB52745806
Tessa T1 3B117K / 6.2 GB105
UIGEN T1.5 3B117K / 6.2 GB71
Qwen2.5 Coder 3B Instruct32K / 6.2 GB196733115
Q2.5 CodeR1 3B32K / 6.2 GB01
VisCoder2 3B32K / 6.2 GB553
Qwen 2.5 Coder 3B SQL Writer32K / 6.2 GB31
Omega Qwen2.5 Coder 3B32K / 6.2 GB823
Arch Agent 3B32K / 6.2 GB428
....5 Coder 3B Instruct Finetuned32K / 6.2 GB90
Note: green Score (e.g. "73.2") means that the model is better than Nexesenex/Qwen_2.5_3b_Smarteaz_0.01a.

Rank the Qwen 2.5 3B Smarteaz 0.01a 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