LLM EXPLORER 63,636 MODELS INDEXED

NaviDC OCR by StarDoc-AI

By StarDoc-AI · 1161 downloads
HF Repo ↗ Copy URL

NaviDC OCR is an open-source language model by StarDoc-AI. Features: 1.4b LLM, VRAM: 2.8GB, Context: 125K, License: apache-2.0, LLM Explorer Score: 0.29.

  Arxiv:2608.12898   Conversational   Custom code   Document-parsing   Document-understanding   En   Endpoints compatible   Image-text-to-text   Ja   Multimodal   Ocr   Qwen2 5 vl   Region:us   Safetensors   Vision   Vision-language   Zh
Model Card on HF 🤗: https://huggingface.co/StarDoc-AI/NaviDC-OCR 

NaviDC OCR Parameters and Internals

LLM NameNaviDC OCR
Repository 🤗https://huggingface.co/StarDoc-AI/NaviDC-OCR 
Model Size1.4b
Required VRAM2.8 GB
Updated2026-08-21
MaintainerStarDoc-AI
Model Typeqwen2_5_vl
Model Files  2.8 GB
Supported Languageszh en ja
Model ArchitectureQwen2_5_VLForConditionalGeneration
Licenseapache-2.0
Context Length128000
Model Max Length128000
Transformers Version4.57.1
Tokenizer ClassQwen2Tokenizer
Padding Token<|endoftext|>
Vocabulary Size151936
Errorsreplace

Best Alternatives to NaviDC OCR

Best Alternatives
Context / RAM
Downloads
Likes
TeleOCR125K / 2.8 GB303831053
TeleOCR125K / 2.8 GB1673930
TeleOCR OQ4 MLX125K / 1.8 GB551
Note: green Score (e.g. "73.2") means that the model is better than StarDoc-AI/NaviDC-OCR.