What are the hardware requirements for TeleOCR?

TeleOCR requires approximately 2.8 GB of VRAM and supports a context window of 125K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed TeleOCR and how large is it?

TeleOCR is developed by StarDoc-AI, a model with 1.4b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate TeleOCR?

TeleOCR is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TeleOCR by StarDoc-AI — VRAM 2.8GB, 125K context

Name: TeleOCR
Author: StarDoc-AI

TeleOCR 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: 0.36.

Arxiv:2608.12898 Conversational Custom code Document-parsing Document-understanding En Endpoints compatible Eval-results 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/TeleOCR

TeleOCR Parameters and Internals

LLM Name	TeleOCR
Repository 🤗	https://huggingface.co/StarDoc-AI/TeleOCR
Model Size	1.4b
Required VRAM	2.8 GB
Updated	2026-09-11
Maintainer	StarDoc-AI
Model Type	qwen2_5_vl
Model Files	2.8 GB
Supported Languages	zh en ja
Model Architecture	Qwen2_5_VLForConditionalGeneration
License	apache-2.0
Context Length	128000
Model Max Length	128000
Transformers Version	4.57.1
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Vocabulary Size	151936
Errors	replace

Rank the TeleOCR capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

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

Best Alternatives to TeleOCR

Best Alternatives	Context / RAM	Downloads	Likes
NaviDC OCR	125K / 2.8 GB	1161	8