--- license: other tags: - ocr - pdf - markdown - layout - text-generation-inference language: - en base_model: - datalab-to/chandra-ocr-2 pipeline_tag: image-text-to-text library_name: transformers --- # **chandra-ocr-2-GGUF** > [Chandra-OCR-2](https://huggingface.co/datalab-to/chandra-ocr-2) from [Datalab](https://huggingface.co/datalab-to) 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.BF16.gguf | BF16 | 9.7 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.BF16.gguf) | | chandra-ocr-2.F16.gguf | F16 | 9.7 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.F16.gguf) | | chandra-ocr-2.Q2_K.gguf | Q2_K | 2.12 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q2_K.gguf) | | chandra-ocr-2.Q3_K_L.gguf | Q3_K_L | 2.69 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q3_K_L.gguf) | | chandra-ocr-2.Q3_K_M.gguf | Q3_K_M | 2.54 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q3_K_M.gguf) | | chandra-ocr-2.Q3_K_S.gguf | Q3_K_S | 2.34 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q3_K_S.gguf) | | chandra-ocr-2.Q4_0.gguf | Q4_0 | 2.9 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q4_0.gguf) | | chandra-ocr-2.Q4_K_M.gguf | Q4_K_M | 3.07 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q4_K_M.gguf) | | chandra-ocr-2.Q4_K_S.gguf | Q4_K_S | 2.92 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q4_K_S.gguf) | | chandra-ocr-2.Q5_0.gguf | Q5_0 | 3.43 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q5_0.gguf) | | chandra-ocr-2.Q5_K_M.gguf | Q5_K_M | 3.51 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q5_K_M.gguf) | | chandra-ocr-2.Q5_K_S.gguf | Q5_K_S | 3.43 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q5_K_S.gguf) | | chandra-ocr-2.Q6_K.gguf | Q6_K | 3.99 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q6_K.gguf) | | chandra-ocr-2.Q8_0.gguf | Q8_0 | 5.16 GB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.Q8_0.gguf) | | chandra-ocr-2.mmproj-bf16.gguf | mmproj-bf16 | 676 MB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.mmproj-bf16.gguf) | | chandra-ocr-2.mmproj-f16.gguf | mmproj-f16 | 676 MB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.mmproj-f16.gguf) | | chandra-ocr-2.mmproj-q8_0.gguf | mmproj-q8_0 | 367 MB | [Download](https://huggingface.co/prithivMLmods/chandra-ocr-2-GGUF/blob/main/chandra-ocr-2.mmproj-q8_0.gguf) | ## 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): ![image.png](https://www.nethype.de/huggingface_embed/quantpplgraph.png)