OvisOCR2 GGUF Quantizations This repository contains GGUF format quantizations of OvisOCR2 , a compact 0.8B end to end model for page level document parsing. The original model was developed by ATH MaaS by post training Qwen3.5 0.8B to parse full document pages directly into clean Markdown (including LaTeX formulas, HTML tables, and layout components). OvisOCR2 establishes a new state of the art for compact document understanding, scoring 96.58 on OmniDocBench v1.6 and outperforming traditional, multi stage layout analysis pipelines. Available Files Main Text Models File Name Precision / Quantization File Size Description : : : : OvisOCR2 F16.gguf 16 bit Float 1.52 GB Baseline unquantized model OvisOCR2 BF16.gguf 16 bit Brain Float 1.52 GB Native weight precision OvisOCR2 Q8 0.gguf 8 bit 812 MB Near identical precision to F16 OvisOCR2 Q6 K.gguf 6 bit 630 MB Excellent balance of size and accuracy OvisOCR2 Q5 K M.gguf 5 bit (Medium) 578 MB Recommended for low resource deployment OvisOCR2 Q5 K S.gguf 5 bit (Small) 564 MB Highly optimized 5 bit layout OvisOCR2 Q4 K M.gguf 4 bit (Medium) 529 MB Standard 4 bit quantization OvisOCR2 Q4 K S.gguf 4 bit (Small) 505 MB Lightweight 4 bit footp…
We use cookies for essential functionality and analytics. You can accept or reject analytics cookies.Cookie policy