chandra-ocr-2-GGUF

Chandra-OCR-2 from Datalab is a state-of-the-art OCR model that outputs structured markdown, HTML, or JSON while preserving precise layout information from images and PDFs across 90+ languages. It achieves SOTA benchmarks with 85.9% on olmocr and 77.8% multilingual score (+12% over Chandra 1), delivering major gains in math equation parsing, complex table reconstruction (including merged cells), handwriting recognition, form elements like checkboxes, and wide-document layouts alongside vastly improved image captioning and diagram extraction. Available via free playground, hosted API for production speed/accuracy, or local deployment through HuggingFace Transformers/vLLM, it excels at transforming challenging real-world documents—financial filings, research papers, historical scans, multilingual forms—into semantically rich structured data for downstream AI pipelines and automation workflows.

Model Files

File Name	Quant Type	File Size	File Link
chandra-ocr-2-Q2_K.gguf	Q2_K	2.12 GB	Download
chandra-ocr-2-Q3_K_L.gguf	Q3_K_L	2.69 GB	Download
chandra-ocr-2-Q3_K_M.gguf	Q3_K_M	2.54 GB	Download
chandra-ocr-2-Q3_K_S.gguf	Q3_K_S	2.34 GB	Download
chandra-ocr-2-Q4_K_M.gguf	Q4_K_M	3.07 GB	Download
chandra-ocr-2-Q4_K_S.gguf	Q4_K_S	2.92 GB	Download
chandra-ocr-2-Q5_K_M.gguf	Q5_K_M	3.51 GB	Download
chandra-ocr-2.BF16.gguf	BF16	9.7 GB	Download
chandra-ocr-2.F16.gguf	F16	9.7 GB	Download
chandra-ocr-2.F32.gguf	F32	19.4 GB	Download
chandra-ocr-2.Q8_0.gguf	Q8_0	5.16 GB	Download
chandra-ocr-2.mmproj-bf16.gguf	mmproj-bf16	676 MB	Download
chandra-ocr-2.mmproj-f16.gguf	mmproj-f16	676 MB	Download
chandra-ocr-2.mmproj-f32.gguf	mmproj-f32	1.33 GB	Download
chandra-ocr-2.mmproj-q8_0.gguf	mmproj-q8_0	367 MB	Download

Quants Usage

(sorted by size, not necessarily quality. IQ-quants are often preferable over similar sized non-IQ quants)

Here is a handy graph by ikawrakow comparing some lower-quality quant types (lower is better):