The visionOCR-3B-061125 model is a fine-tuned version of Qwen/Qwen2.5-VL-3B-Instruct, optimized for Document-Level Optical Character Recognition (OCR), long-context vision-language understanding, and accurate image-to-text conversion with mathematical LaTeX formatting. Built on top of the Qwen2.5-VL architecture, this model significantly improves document comprehension, structured data extraction, and visual reasoning across diverse input formats.

Model Files

File Name	Size	Format	Description
visionOCR-3B-061125-BF16.gguf	6.18 GB	BF16	Brain floating point 16-bit
visionOCR-3B-061125-Q6_K.gguf	2.54 GB	Q6_K	6-bit quantized
visionOCR-3B-061125-Q5_K_M.gguf	2.22 GB	Q5_K_M	5-bit quantized, medium quality
visionOCR-3B-061125-Q4_K_M.gguf	1.93 GB	Q4_K_M	4-bit quantized, medium quality
visionOCR-3B-061125-Q3_K_M.gguf	1.59 GB	Q3_K_M	3-bit quantized, medium quality
visionOCR-3B-061125-Q3_K_S.gguf	1.45 GB	Q3_K_S	3-bit quantized, small quality
visionOCR-3B-061125-Q2_K.gguf	1.27 GB	Q2_K	2-bit quantized

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):

prithivMLmods/visionOCR-3B-061125-GGUF

visionOCR-3B-061125-GGUF

Model Files

Quants Usage

prithivMLmods/
visionOCR-3B-061125-GGUF