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

Octopus Planning by NexaAIDev

 »  All LLMs  »  NexaAIDev  »  Octopus Planning   URL Share it on

  18   
  Arxiv:2406.18082   Autotrain compatible   Conversational   Custom code   Endpoints compatible   Phi3   Region:us   Safetensors   Sharded   Tensorflow
Model Card on HF 🤗: https://huggingface.co/NexaAIDev/octopus-planning 

Octopus Planning Benchmarks

LLME Score: 0.16719
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
Octopus Planning (NexaAIDev/octopus-planning)
🌟 Advertise your project 🚀

Octopus Planning Parameters and Internals

Model Type 
on-device language model
Use Cases 
Areas:
edge devices, AI Agents
Additional Notes 
Octo-planner enables rapid and efficient planning without the need for cloud connectivity, emphasizing on-device operation for privacy and efficiency.
Training Details 
Data Sources:
10 Android API descriptions
LLM NameOctopus Planning
Repository 🤗https://huggingface.co/NexaAIDev/octopus-planning 
Model Size3.8b
Required VRAM7.7 GB
Updated2025-07-21
MaintainerNexaAIDev
Model Typephi3
Model Files  5.0 GB: 1-of-2   2.7 GB: 2-of-2
Model ArchitecturePhi3ForCausalLM
Licensecc-by-nc-4.0
Context Length131072
Model Max Length131072
Transformers Version4.39.3
Tokenizer ClassLlamaTokenizer
Padding Token<|endoftext|>
Vocabulary Size32064
Torch Data Typebfloat16

Best Alternatives to Octopus Planning

Best Alternatives
Context / RAM
Downloads
Likes
Phi 4 Mini Instruct128K / 7.7 GB240353590
Phi 3 Mini 128K Instruct128K / 7.7 GB10640591668
Phi 3.5 Mini Instruct128K / 7.7 GB218890906
Phi 4 Mini Reasoning128K / 7.7 GB9758202
MediPhi Instruct128K / 7.7 GB449344
NuExtract 1.5128K / 7.7 GB68154237
Phi 4 Mini Reasoning128K / 7.7 GB45372
NuExtract V1.5128K / 7.7 GB10851189
MediPhi Clinical128K / 7.7 GB9069
Phi 4 Mini Instruct128K / 7.7 GB576920
Note: green Score (e.g. "73.2") means that the model is better than NexaAIDev/octopus-planning.

Rank the Octopus Planning 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? 51187 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.
Release v20241124
  Support LLM Explorer