What are the hardware requirements for SenOCR Vi?

SenOCR Vi requires approximately 3.8 GB of VRAM and supports a context window of 128K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed SenOCR Vi and how large is it?

SenOCR Vi is developed by VietAlphaLabs, a model with 958.6m 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 SenOCR Vi?

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

SenOCR Vi by VietAlphaLabs — VRAM 3.8GB, 128K context

Name: SenOCR Vi
Author: VietAlphaLabs

SenOCR Vi is an open-source language model by VietAlphaLabs. Features: 958.6m LLM, VRAM: 3.8GB, Context: 128K, License: apache-2.0, LLM Explorer Score: 0.3.

Arxiv:2408.12480 Base model:finetune:paddlepadd... Base model:paddlepaddle/paddle... Conversational Custom code Dataset:5cd-ai/viet-handwritin... Document-ai Document-parsing En Endpoints compatible Image-text-to-text Image-to-text Ocr Paddleocr Paddleocr vl Region:us Safetensors Sharded Tensorflow Vi Vietnamese Zh

Model Card on HF 🤗: https://huggingface.co/VietAlphaLabs/SenOCR-Vi

SenOCR Vi Parameters and Internals

LLM Name	SenOCR Vi
Repository 🤗	https://huggingface.co/VietAlphaLabs/SenOCR-Vi
Base Model(s)	PaddlePaddle/PaddleOCR-VL-1.6 PaddlePaddle/PaddleOCR-VL-1.6
Model Size	958.6m
Required VRAM	3.8 GB
Updated	2026-09-06
Maintainer	VietAlphaLabs
Model Type	paddleocr_vl
Model Files	3.8 GB: 1-of-1
Supported Languages	vi en zh
Model Architecture	PaddleOCRVLForConditionalGeneration
License	apache-2.0
Context Length	131072
Model Max Length	131072
Transformers Version	4.55.0
Tokenizer Class	LlamaTokenizer
Padding Token	<unk>
Vocabulary Size	103424
Torch Data Type	bfloat16

Rank the SenOCR Vi 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 SenOCR Vi

Best Alternatives	Context / RAM	Downloads	Likes
PaddleOCR VL 1.6	128K / 1.9 GB	57951	401
PaddleOCR VL 1.5	128K / 1.9 GB	14943	663

Note: green Score (e.g. "73.2") means that the model is better than VietAlphaLabs/SenOCR-Vi.