What are the hardware requirements for OpenThai2.0 OCR Markdown?

OpenThai2.0 OCR Markdown requires approximately 2.5 GB of VRAM and supports a context window of 16K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed OpenThai2.0 OCR Markdown and how large is it?

OpenThai2.0 OCR Markdown is developed by iapp, a model with 630.8m 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 OpenThai2.0 OCR Markdown?

OpenThai2.0 OCR Markdown is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

OpenThai2.0 OCR Markdown by iapp — VRAM 2.5GB, 16K context

Name: OpenThai2.0 OCR Markdown
Author: iapp

OpenThai2.0 OCR Markdown is an open-source language model by iapp. Features: 630.8m LLM, VRAM: 2.5GB, Context: 16K, License: other, LLM Explorer Score: 0.46.

Base model:finetune:nvidia/nem... Base model:nvidia/nemotron-3.5... Conversational Custom code Document-parsing En Image-text-to-text Markdown Nemotron Nemotron parse Ocr Region:us Safetensors Tables Th Thai

Model Card on HF 🤗: https://huggingface.co/iapp/OpenThai2.0-OCR-Markdown

OpenThai2.0 OCR Markdown Parameters and Internals

LLM Name	OpenThai2.0 OCR Markdown
Repository 🤗	https://huggingface.co/iapp/OpenThai2.0-OCR-Markdown
Base Model(s)	nvidia/Nemotron-3.5-Parse nvidia/Nemotron-3.5-Parse
Model Size	630.8m
Required VRAM	2.5 GB
Updated	2026-11-13
Maintainer	iapp
Model Type	nemotron_parse
Model Files	2.5 GB
Supported Languages	th en
Model Architecture	RadioMBartPrefixForCausalLM
License	other
Context Length	16384
Model Max Length	16384
Transformers Version	5.6.1
Tokenizer Class	PreTrainedTokenizerFast
Padding Token	<pad>
Vocabulary Size	72512
Torch Data Type	bfloat16

Rank the OpenThai2.0 OCR Markdown 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 OpenThai2.0 OCR Markdown

Best Alternatives	Context / RAM	Downloads	Likes
Nemotron 3.5 Parse	16K / 2.5 GB	1799	74