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

APT3 1B Instruct V1 by Azurro

 »  All LLMs  »  Azurro  »  APT3 1B Instruct V1   URL Share it on

  11   

APT3 1B Instruct V1 is an open-source language model by Azurro. Features: 1b LLM, VRAM: 4.2GB, Context: 2K, License: cc-by-nc-4.0, Fine-Tuned, Instruction-Based, LLM Explorer Score: 0.11.

  Allamo   Finetuned   Instruct   Llama   Pl   Region:us   Safetensors
Model Card on HF 🤗: https://huggingface.co/Azurro/APT3-1B-Instruct-v1 

APT3 1B Instruct V1 Benchmarks

LLME Score: 0.11267
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
APT3 1B Instruct V1 (Azurro/APT3-1B-Instruct-v1)
🌟 Advertise your project 🚀

APT3 1B Instruct V1 Parameters and Internals

Model Type 
causal decoder-only, transformer
Use Cases 
Areas:
Scientific purposes, Private use
Limitations:
No moderation mechanisms available, Can produce factually incorrect or offensive outputs
Additional Notes 
The model does not constitute legal advice. Responsibility on third-party actions not accepted.
Supported Languages 
Polish (Native and primary language)
Training Details 
Data Sources:
Speakleash, Azurro's proprietary dataset
Data Volume:
285 GB of text corpus
Methodology:
Fine-tuned with 2.5 million instructions over two epochs on over 1 billion tokens
Hardware Used:
Nvidia RTX 4090 24GB VRAM
Model Architecture:
Transformer architecture similar to Meta AI's LLaMA models
Input Output 
Input Format:
Prompt should be surrounded by `[INST]` and `[/INST]` tokens.
Accepted Modalities:
text
Output Format:
Generated completion is finished by the end-of-sentence token.
LLM NameAPT3 1B Instruct V1
Repository 🤗https://huggingface.co/Azurro/APT3-1B-Instruct-v1 
Model Size1b
Required VRAM4.2 GB
Updated2026-05-01
MaintainerAzurro
Model Typellama
Instruction-BasedYes
Model Files  4.2 GB
Supported Languagespl
Model ArchitectureLlamaForCausalLM
Licensecc-by-nc-4.0
Context Length2048
Model Max Length2048
Transformers Version4.35.2
Tokenizer ClassPreTrainedTokenizerFast
Vocabulary Size31980
Torch Data Typefloat32

Best Alternatives to APT3 1B Instruct V1

Best Alternatives
Context / RAM
Downloads
Likes
Llama 3.2 1B Instruct128K / 2.5 GB63368191393
...2 1B Instruct Only Mask W Item128K / 3 GB25300
Llama 3.2 1B Instruct Bf16128K / 2.5 GB11585
Llama 3.2 1B Instruct128K / 2.5 GB70
...Instruct Only Mask W Item Mesh128K / 3 GB3850
Shield Llama 3.2 1B Full FT CE128K / 2.5 GB7950
Llama3.2 1B FantasySciFi128K / 2.5 GB3040
Llama 3.2 1B Instruct128K / 2.5 GB15769192
Llama 3.2 OctoThinker INano 1B128K / 3 GB2421
Llama Nexora Vector V0.1128K / 2.5 GB361
Note: green Score (e.g. "73.2") means that the model is better than Azurro/APT3-1B-Instruct-v1.

Rank the APT3 1B Instruct V1 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