What are the hardware requirements for Chandra Ocr 2?

Chandra Ocr 2 requires approximately 10.6 GB of VRAM. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Chandra Ocr 2 and how large is it?

Chandra Ocr 2 is developed by datalab-to, a model with 5.3b 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 Chandra Ocr 2?

Chandra Ocr 2 is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Chandra Ocr 2 by datalab-to — VRAM 10.6GB

Name: Chandra Ocr 2
Author: datalab-to

Chandra Ocr 2 is an open-source language model by datalab-to. Features: 5.3b LLM, VRAM: 10.6GB, License: openrail, LLM Explorer Score: 0.41.

Conversational Deploy:azure Endpoints compatible Eval-results Image-text-to-text Layout Markdown Ocr Pdf Qwen3 5 Region:us Safetensors

Model Card on HF 🤗: https://huggingface.co/datalab-to/chandra-ocr-2

Chandra Ocr 2 Parameters and Internals

LLM Name	Chandra Ocr 2
Repository 🤗	https://huggingface.co/datalab-to/chandra-ocr-2
Model Size	5.3b
Required VRAM	10.6 GB
Updated	2026-08-09
Maintainer	datalab-to
Model Type	qwen3_5
Model Files	10.6 GB
Model Architecture	Qwen3_5ForConditionalGeneration
License	openrail
Model Max Length	262144
Transformers Version	5.2.0
Tokenizer Class	Qwen2Tokenizer
Padding Token	<\|endoftext\|>
Errors	replace

Rank the Chandra Ocr 2 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 Chandra Ocr 2

Best Alternatives	Context / RAM	Downloads	Likes
Salad	0K / 10.6 GB	34	1