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

P1 V3 by abcorrea

 »  All LLMs  »  abcorrea  »  P1 V3   URL Share it on

  5   

P1 V3 is an open-source language model by abcorrea. Features: 4b LLM, VRAM: 8.1GB, Context: 40K, LLM Explorer Score: 0.19.

  Base model:abcorrea/p1-v2 Base model:finetune:abcorrea/p...   Conversational   Endpoints compatible   Generated from trainer   Qwen3   Region:us   Safetensors   Sft   Sharded   Tensorflow   Trl
Model Card on HF 🤗: https://huggingface.co/abcorrea/p1-v3 

P1 V3 Benchmarks

LLME Score: 0.19374
nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").
P1 V3 (abcorrea/p1-v3)
🌟 Advertise your project 🚀

P1 V3 Parameters and Internals

LLM NameP1 V3
Repository 🤗https://huggingface.co/abcorrea/p1-v3 
Model Namep1-v3
Base Model(s)  P1 V2   abcorrea/p1-v2
Model Size4b
Required VRAM8.1 GB
Updated2026-05-01
Maintainerabcorrea
Model Typeqwen3
Model Files  5.0 GB: 1-of-2   3.1 GB: 2-of-2   0.0 GB
Model ArchitectureQwen3ForCausalLM
Context Length40960
Model Max Length40960
Transformers Version4.52.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151680
Torch Data Typebfloat16
Errorsreplace

Best Alternatives to P1 V3

Best Alternatives
Context / RAM
Downloads
Likes
FastContext 1.0 4B SFT256K / 8.1 GB5735357
Fable Traces256K / 8.1 GB277157
Qwen3 4B Instruct 2507256K / 8.1 GB5376006894
FastContext 1.0 4B RL256K / 8.1 GB455961
GRPO 4 70256K / 8.1 GB50
Qwen3 4B Thinking 2507256K / 8.1 GB529167601
Lightning 4B256K / 8.1 GB136
Qwen3 4B Instruct 2507 FP8256K / 5.2 GB92454678
AgentCPM Explore256K / 8.9 GB499415
FastContext 1.0 4B SFT256K / 8.1 GB11313
Note: green Score (e.g. "73.2") means that the model is better than abcorrea/p1-v3.

Rank the P1 V3 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? 54931 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