Model reference · open weights
chandra-ocr-2 is an open-weight language model from datalab-to, listed in the AxForge catalogue. AxForge can bring it up on EU-owned hardware for you on request — with the licence handled where one is required.
About
Chandra OCR 2 Chandra 2 is a state of the art OCR model from Datalab that outputs markdown, HTML, and JSON. It is highly accurate at extracting text from images and PDFs, while preserving layout information. Try Chandra in the free playground, or use the hosted API for higher accuracy and speed. What's New in Chandra 2 - 85.8% olmocr bench score (sota), 77.8% multilingual bench score (12% improvement over Chandra 1) - Significant improvements to math, tables, complex layouts - Improved layout, especially on wider documents - Significantly better image captioning - 90+ language support with major accuracy gains Features - Convert documents to markdown, HTML, or JSON with detailed layout information - Excellent handwriting support - Reconstructs forms accurately, including checkboxes - Strong performance with tables, math, and complex layouts - Extracts images and diagrams, with captions and structured data - Support for 90+ languages Quickstart Usage With vLLM (recommended) With HuggingFace Transformers Benchmarks olmOCR Benchmark Examples Multilingual Benchmark (43 Languages) The table below covers the 43 most common languages, benchmarked across multiple models. For a comprehensive evaluation across 90 languages (Chandra 2 vs Gemini 2.5 Flash only), see the full 90-language benchmark. Full 90-Language Benchmark We also have a more comprehensive evaluation covering 90 languages, comparing Chandra 2 against Gemini 2.5 Flash. The average scores are lower than the 43-language table above because this includes many lower-resource languages. Chandra 2 averages 72.7% vs Gemini 2.5 Flash at 60.8%. See the full 90-language results. Throughput Benchmarked with vLLM on a single NVIDIA H100 80GB GPU using a diverse mix of documents (math, tables, scans, multi-column layouts) from the olmOCR benchmark set. This set is significantly slower than real-world usage - we estimate 2 pages/s in real-world usage. Commercial Usage Code is Apache 2.0. Model weights use a modified OpenRAIL-M license: free for research, personal use, and startups under $2M funding/revenue. Cannot be used competitively with our API. For broader commercial licensing, see pricing. Credits - Huggingface Tra
Summarised from the published model card. Read the full card on the HuggingFace links below.
Specifications
| Maker | datalab-to |
|---|---|
| Type | Language models |
| Parameters (lead) | 5.3B |
| Variants | 1 |
| Runs with | transformers |
| Released | 2026-03-16 |
| Popularity | 2.9M downloads / month |
| Likes | 481 |
| Licence | Open weights |
How it works
Variants
Open weights ship in several sizes and precisions. One page, all the variants — pick the one that fits your GPU. VRAM figures are estimates from model size.
| Variant | Params | Precision | VRAM | Fits 16 GB | Weights |
|---|---|---|---|---|---|
| chandra-ocr-2 | 5.3B | BF16 | ~12.2 GB | ✓ | Weights ↗ |
Using it via the API
Once AxForge deploys chandra-ocr-2 for you, it answers on the OpenAI-compatible API — the same base URL and keys as every other model. (chandra-ocr-2 below is illustrative; you get the exact model name on deployment.)
$ curl -sS https://api.axforge.ai/v1/chat/completions \
-H "Authorization: Bearer $AXFORGE_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"chandra-ocr-2","messages":[{"role":"user","content":"Hello"}]}'
Details
Tags
Licence
Open weights under openrail — commercial use is permitted. Deploy it on AxForge EU hardware on request. Read the licence ↗