What are the hardware requirements for TeleOCR INT8?

TeleOCR INT8 requires approximately 2 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 INT8 and how large is it?

TeleOCR INT8 is developed by sahilchachra, a model with 1.3b 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 INT8?

TeleOCR INT8 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TeleOCR INT8 by sahilchachra — VRAM 2GB, 125K context

Name: TeleOCR INT8
Author: sahilchachra

TeleOCR INT8 is an open-source language model by sahilchachra. Features: 1.3b LLM, VRAM: 2GB, Context: 125K, License: apache-2.0, LLM Explorer Score: 0.3.

8-bit Apple-silicon Base model:quantized:xingchen-... Base model:xingchen-agi/teleoc... Conversational Custom code Document-parsing En Image-text-to-text Int8 Mlx Multimodal Ocr Qwen2 5 vl Region:us Safetensors Zh

Model Card on HF 🤗: https://huggingface.co/sahilchachra/TeleOCR-INT8

TeleOCR INT8 Parameters and Internals

LLM Name	TeleOCR INT8
Repository 🤗	https://huggingface.co/sahilchachra/TeleOCR-INT8
Base Model(s)	TeleOCR XingChen-AGI/TeleOCR
Model Size	1.3b
Required VRAM	2 GB
Updated	2026-10-05
Maintainer	sahilchachra
Model Type	qwen2_5_vl
Model Files	2.0 GB
Supported Languages	zh en
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 INT8 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 INT8

Best Alternatives	Context / RAM	Downloads	Likes
TeleOCR MXFP8	125K / 1.9 GB	163	2

Note: green Score (e.g. "73.2") means that the model is better than sahilchachra/TeleOCR-INT8.