LLM EXPLORER 62,589 MODELS INDEXED

TeleOCR by XingChen-AGI

By XingChen-AGI · 30383 downloads

TeleOCR is an open-source language model by XingChen-AGI. Features: 1.4b LLM, VRAM: 2.8GB, Context: 125K, License: apache-2.0, LLM Explorer Score: 0.48.

  Arxiv:2608.12898   Conversational   Custom code   Document-parsing   En   Endpoints compatible   Eval-results   Image-text-to-text   Multimodal   Ocr   Qwen2 5 vl   Region:us   Safetensors   Zh
Model Card on HF πŸ€—: https://huggingface.co/XingChen-AGI/TeleOCR 

TeleOCR Parameters and Internals

LLM NameTeleOCR
Repository πŸ€—https://huggingface.co/XingChen-AGI/TeleOCR 
Model Size1.4b
Required VRAM2.8 GB
Updated2026-09-30
MaintainerXingChen-AGI
Model Typeqwen2_5_vl
Model Files  2.8 GB
Supported Languageszh en
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 TeleOCR

Best Alternatives
Context / RAM
Downloads
Likes
TeleOCR125K / 2.8 GB1673930
NaviDC OCR125K / 2.8 GB11618