PR

Proxima Ocr D.Markdown Post3.0.L

ProximaGGUF by mradermacherUpdated 2025-12-10
Download on Hugging Face
Parameters8.19B
Context256K
Layers36
Architectureqwen3vl
Smallest quant0.0 GB
Quick answer

Proxima Ocr D.Markdown Post3.0.L needs about 6.7 GB of memory at Q4_K_M (a 5.0 GB file) with an 8K context window, so it fits on a 8 GB GPU. This repository has 25 quants, from 0.0 GB to 6.7 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 4.8 GB.

Proxima Ocr D.Markdown Post3.0.L – Vision‑to‑Markdown OCR model

Proxima Ocr D.Markdown Post3.0.L is a vision model fine‑tuned on Qwen3‑VL‑8B‑Instruct. It converts scanned documents into Markdown, HTML‑Markdown, and enriched formats with inline code and LaTeX. The model supports complex layout interpretation and multi‑page reasoning.

Good at

  • High‑fidelity OCR of structured documents
  • Markdown and HTML‑Markdown reconstruction
  • Multi‑page document reasoning

Limits

  • Requires significant GPU VRAM for long sequences
  • Accuracy drops on heavily damaged scans
  • No native vision support beyond OCR

Best for

  • OCR to Markdown conversion
  • Table and form extraction
  • Enterprise document automation

Who it’s for. Developers and data engineers needing precise document conversion and structured output. Ideal for teams building knowledge bases or automating documentation workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 1.7 GB
Fits Get file →
IQ1_S2.1 GB 3.8 GB
Fits Get file →
IQ1_M2.3 GB 4.0 GB
Fits Get file →
IQ2_XXS2.5 GB 4.2 GB
Fits Get file →
IQ2_XS2.7 GB 4.4 GB
Fits Get file →
IQ2_S2.9 GB 4.6 GB
Fits Get file →
IQ2_M3.1 GB 4.8 GB
Fits Get file →
Q2_K_S3.1 GB 4.8 GB
Fits Get file →
Q2_K3.3 GB 5.0 GB
Fits Get file →
IQ3_XXS3.4 GB 5.1 GB
Fits Get file →
IQ3_XS3.6 GB 5.3 GB
Fits Get file →
Q3_K_S3.8 GB 5.5 GB
Fits Get file →
IQ3_S3.8 GB 5.5 GB
Fits Get file →
IQ3_M3.9 GB 5.6 GB
Fits Get file →
Q3_K_M4.1 GB 5.8 GB
Fits Get file →
Q3_K_L4.4 GB 6.1 GB
Fits Get file →
IQ4_XS4.6 GB 6.3 GB
Fits Get file →
Q4_04.8 GB 6.5 GB
Fits Get file →
IQ4_NL4.8 GB 6.5 GB
Fits Get file →
Q4_K_S4.8 GB 6.5 GB
Fits Get file →
Q4_K_M5.0 GB 6.7 GB
Fits Get file →
Q4_15.2 GB 7.0 GB
Fits Get file →
Q5_K_S5.7 GB 7.4 GB
Tight Get file →
Q5_K_M5.9 GB 7.6 GB
Tight Get file →
Q6_K6.7 GB 8.4 GB
Too big Get file →

For 8 GB VRAM, use IQ1_S (2.12 GB, 3.8 GB memory) or Q2_K (3.28 GB, 5 GB memory). If 12 GB VRAM is available, Q3_K_M (4.12 GB, 5.8 GB memory) offers higher quality. Larger models like Q6_K (6.73 GB, 8.4 GB memory) require 16 GB or more.

What GPU do you need for Proxima Ocr D.Markdown Post3.0.L?

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 IQ1_M (2.3 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q3_K_M (4.1 GB file, about 5.8 GB in use).
  • 8 GB VRAM: the best quant that fits is Q5_K_M (5.9 GB file, about 7.6 GB in use).
  • 12 GB VRAM: the best quant that fits is Q6_K (6.7 GB file, about 8.4 GB in use).

Which Proxima Ocr D.Markdown Post3.0.L quant should you choose?

Q4_K_M is the usual starting point for Proxima Ocr D.Markdown Post3.0.L: it balances file size and quality well. Here it is a 5.0 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

Architectureqwen3vl
Parameters8.19B
Layers36
Trained context262,144 tokens
KV cache (fp16)144 KB per token

Source

Quantized bymradermacher
FamilyProxima
Licenseapache-2.0
Downloads (HF)762
Last updated2025-12-10

Frequently asked questions about Proxima Ocr D.Markdown Post3.0.L

How much VRAM does Proxima Ocr D.Markdown Post3.0.L need?

About 6.7 GB at Q4_K_M with an 8K context window. That is the 5.0 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 Proxima Ocr D.Markdown Post3.0.L on an 8 GB GPU?

Yes, with Q5_K_M: the 5.9 GB file needs about 7.6 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Proxima Ocr D.Markdown Post3.0.L GGUF?

It depends on the quant: file is 0.0 GB, IQ1_S is 2.1 GB, IQ1_M is 2.3 GB, IQ2_XXS is 2.5 GB, IQ2_XS is 2.7 GB, IQ2_S is 2.9 GB and 19 more.

What context length does Proxima Ocr D.Markdown Post3.0.L support?

The GGUF header lists a trained context length of 262,144 tokens (256K). The KV cache grows with the context you use: about 1.2 GB at 8K and 4.8 GB at 32K.

Where can I download Proxima Ocr D.Markdown Post3.0.L GGUF?

The files are on Hugging Face in the mradermacher/proxima-ocr-d.markdown-post3.0.l-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 Proxima Ocr D.Markdown Post3.0.L use?

Hugging Face lists the license as apache-2.0. 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 Proxima Ocr D.Markdown Post3.0.L on 8 GB VRAM?

Yes, use the IQ1_S quant which requires about 3.8 GB memory at 8 k context.

Does the model support multi‑page documents?

Yes, it supports multi‑page chunking and cross‑reference recognition.

What license applies to this model?

The model is released under the apache-2.0 license.

Other GGUFs of proxima-ocr-d.markdown-post3.0.l

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Proxima models

All Proxima →

Other small models

All small models →