EP

Epsilon Ocr D.Markdown Post3.0.M

EpsilonGGUF by mradermacherUpdated 2025-12-26
Download on Hugging Face
Parameters3.09B
Context125K
Layers36
Architectureqwen2vl
Smallest quant0.0 GB
Quick answer

Epsilon Ocr D.Markdown Post3.0.M needs about 2.7 GB of memory at Q4_K_M (a 1.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 25 quants, from 0.0 GB to 2.5 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 1.2 GB.

Epsilon Ocr D.Markdown Post3.0.M – multimodal OCR and Markdown generation

Epsilon Ocr D.Markdown Post3.0.M is a vision model fine‑tuned on Qwen2.5‑VL‑3B‑Instruct. It converts documents into structured Markdown, HTML‑Markdown, and hybrid technical formats while embedding code blocks. The model supports long‑document reasoning and complex layout extraction.

Good at

  • OCR to Markdown conversion
  • Table and form extraction
  • Multimodal long‑document reasoning

Limits

  • Accuracy drops on highly damaged or low‑resolution images
  • Limited performance on very large document reasoning
  • Language coverage varies for low‑resource scripts

Best for

  • Digitizing manuals and books
  • Reconstructing research papers
  • Automating enterprise knowledge workflows

Who it’s for. Developers and researchers needing OCR‑driven document reconstruction and structured Markdown output. Suitable for teams that handle multi‑page documents, tables, and code snippets.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.8 GB
Fits Get file →
IQ1_S0.8 GB 1.6 GB
Fits Get file →
IQ1_M0.9 GB 1.7 GB
Fits Get file →
IQ2_XXS0.9 GB 1.8 GB
Fits Get file →
IQ2_XS1.0 GB 1.8 GB
Fits Get file →
IQ2_S1.1 GB 1.9 GB
Fits Get file →
IQ2_M1.1 GB 1.9 GB
Fits Get file →
Q2_K_S1.2 GB 2.0 GB
Fits Get file →
Q2_K1.3 GB 2.1 GB
Fits Get file →
IQ3_XXS1.3 GB 2.1 GB
Fits Get file →
IQ3_XS1.4 GB 2.2 GB
Fits Get file →
Q3_K_S1.5 GB 2.3 GB
Fits Get file →
IQ3_S1.5 GB 2.3 GB
Fits Get file →
IQ3_M1.5 GB 2.3 GB
Fits Get file →
Q3_K_M1.6 GB 2.4 GB
Fits Get file →
Q3_K_L1.7 GB 2.5 GB
Fits Get file →
IQ4_XS1.7 GB 2.5 GB
Fits Get file →
IQ4_NL1.8 GB 2.6 GB
Fits Get file →
Q4_01.8 GB 2.6 GB
Fits Get file →
Q4_K_S1.8 GB 2.6 GB
Fits Get file →
Q4_K_M1.9 GB 2.7 GB
Fits Get file →
Q4_12.0 GB 2.8 GB
Fits Get file →
Q5_K_S2.2 GB 3.0 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.5 GB 3.3 GB
Fits Get file →

For 8 GB VRAM, use IQ1_S (0.79 GB, 1.6 GB memory) or IQ1_M (0.85 GB, 1.7 GB). For 12 GB VRAM, IQ2_M (1.14 GB, 1.9 GB) or Q3_K_M (1.59 GB, 2.4 GB) provide a balance of size and memory. Higher quants like Q5_K_M (2.22 GB, 3 GB) require 16 GB or more.

What GPU do you need for Epsilon Ocr D.Markdown Post3.0.M?

These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.

  • 4 GB VRAM: the best quant that fits is Q6_K (2.5 GB file, about 3.3 GB in use).

Which Epsilon Ocr D.Markdown Post3.0.M quant should you choose?

Q4_K_M is the usual starting point for Epsilon Ocr D.Markdown Post3.0.M: it balances file size and quality well. Here it is a 1.9 GB file.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureqwen2vl
Parameters3.09B
Layers36
Trained context128,000 tokens
KV cache (fp16)36 KB per token

Source

Quantized bymradermacher
FamilyEpsilon
Licenseother
Downloads (HF)876
Last updated2025-12-26

Frequently asked questions about Epsilon Ocr D.Markdown Post3.0.M

How much VRAM does Epsilon Ocr D.Markdown Post3.0.M need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 1.9 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.

Can I run Epsilon Ocr D.Markdown Post3.0.M on an 8 GB GPU?

Yes, with Q6_K: the 2.5 GB file needs about 3.3 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Epsilon Ocr D.Markdown Post3.0.M GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 0.8 GB, IQ1_M is 0.9 GB, IQ2_XXS is 0.9 GB, IQ2_XS is 1.0 GB, IQ2_S is 1.1 GB and 19 more.

What context length does Epsilon Ocr D.Markdown Post3.0.M support?

The GGUF header lists a trained context length of 128,000 tokens (125K). The KV cache grows with the context you use: about 0.3 GB at 8K and 1.2 GB at 32K.

Where can I download Epsilon Ocr D.Markdown Post3.0.M GGUF?

The files are on Hugging Face in the mradermacher/epsilon-ocr-d.markdown-post3.0.m-i1-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does Epsilon Ocr D.Markdown Post3.0.M use?

Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.

Can I run this model on 8 GB VRAM?

Yes, the IQ1_S quant uses 1.6 GB memory at 8 k context, fitting within 8 GB VRAM.

Does the model support image input?

Yes, it is a vision model and accepts image inputs for OCR and layout analysis.

What is the context length?

The model was trained with 128000 tokens context length.

Other GGUFs of epsilon-ocr-d.markdown-post3.0.m

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Epsilon models

All Epsilon →

Other tiny models

All tiny models →