docscopeOCR-7B-050425-exp-GGUF

The docscopeOCR-7B-050425-exp model is a fine-tuned version of Qwen/Qwen2.5-VL-7B-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 File

File Name	Size	Format	Description
docscopeOCR-7B-050425-exp.IQ4_XS.gguf	4.25 GB	GGUF (IQ4_XS)	Int4 extra-small quantized model
docscopeOCR-7B-050425-exp.Q2_K.gguf	3.02 GB	GGUF (Q2_K)	2-bit quantized model
docscopeOCR-7B-050425-exp.Q3_K_L.gguf	4.09 GB	GGUF (Q3_K_L)	3-bit large quantized model
docscopeOCR-7B-050425-exp.Q3_K_M.gguf	3.81 GB	GGUF (Q3_K_M)	3-bit medium quantized model
docscopeOCR-7B-050425-exp.Q3_K_S.gguf	3.49 GB	GGUF (Q3_K_S)	3-bit small quantized model
docscopeOCR-7B-050425-exp.Q4_K_M.gguf	4.68 GB	GGUF (Q4_K_M)	4-bit medium quantized model
docscopeOCR-7B-050425-exp.Q5_K_M.gguf	5.44 GB	GGUF (Q5_K_M)	5-bit medium quantized model
docscopeOCR-7B-050425-exp.Q5_K_S.gguf	5.32 GB	GGUF (Q5_K_S)	5-bit small quantized model
docscopeOCR-7B-050425-exp.Q6_K.gguf	6.25 GB	GGUF (Q6_K)	6-bit quantized model
docscopeOCR-7B-050425-exp.Q8_0.gguf	8.1 GB	GGUF (Q8_0)	8-bit quantized model
config.json	36 B	JSON	Configuration file
.gitattributes	2.25 kB	Text	Git attributes configuration

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):