What are the hardware requirements for TeleOCR OQ4 MLX?

TeleOCR OQ4 MLX requires approximately 1.8 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 OQ4 MLX and how large is it?

TeleOCR OQ4 MLX is developed by groxaxo, 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 OQ4 MLX?

TeleOCR OQ4 MLX is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

TeleOCR OQ4 MLX by groxaxo — VRAM 1.8GB, 125K context

Name: TeleOCR OQ4 MLX
Author: groxaxo

TeleOCR OQ4 MLX is an open-source language model by groxaxo. Features: 1.4b LLM, VRAM: 1.8GB, Context: 125K, License: apache-2.0, LLM Explorer Score: 0.29.

4-bit Base model:quantized:xingchen-... Base model:xingchen-agi/teleoc... Conversational Custom code En Image-text-to-text Mlx Ocr Omlx Quantized Qwen2.5-vl Qwen2 5 vl Region:us Safetensors Teleocr Zh

Model Card on HF 🤗: https://huggingface.co/groxaxo/TeleOCR-oQ4-MLX

TeleOCR OQ4 MLX Parameters and Internals

LLM Name	TeleOCR OQ4 MLX
Repository 🤗	https://huggingface.co/groxaxo/TeleOCR-oQ4-MLX
Base Model(s)	TeleOCR XingChen-AGI/TeleOCR
Model Size	1.4b
Required VRAM	1.8 GB
Updated	2026-10-10
Maintainer	groxaxo
Model Type	qwen2_5_vl
Model Files	1.8 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 OQ4 MLX 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 OQ4 MLX

Best Alternatives	Context / RAM	Downloads	Likes
TeleOCR	125K / 2.8 GB	30383	1053
TeleOCR	125K / 2.8 GB	16739	30
NaviDC OCR	125K / 2.8 GB	1161	8

Note: green Score (e.g. "73.2") means that the model is better than groxaxo/TeleOCR-oQ4-MLX.