UN

Unlimited OCR

UnlimitedGGUF by sahilchachraUpdated 2026-07-01
Download on Hugging Face
Parameters2.93B
Context—
Layers—
Architecturedeepseek2-ocr
Smallest quant1.2 GB
Quick answer

Unlimited OCR needs about 2.7 GB of memory at Q4_K_M (a 2.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 13 quants, from 1.2 GB (IQ2_M) to 5.9 GB (BF16).

3B vision‑language OCR model for one‑shot long‑horizon parsing

Unlimited OCR is a 2.93B parameter vision‑language model based on DeepSeek‑OCR. It supports long‑horizon document parsing with a single prompt. The model is released under the MIT license and requires a DeepSeek‑OCR‑aware llama.cpp build.

Good at

  • One‑shot OCR of long documents
  • Accurate bounding box extraction
  • High‑throughput inference with vLLM

Limits

  • Requires DeepSeek‑OCR‑aware llama.cpp build
  • No native vision support in stock llama.cpp
  • Large VRAM needed for higher‑quality quants

Best for

  • Batch OCR of PDFs
  • Generating structured Markdown from scanned pages
  • Extracting tables and headings from documents

Who it’s for. Developers building OCR pipelines who need a lightweight, open‑source model. Researchers testing long‑horizon OCR performance. Teams integrating OCR into document‑analysis workflows.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
IQ2_M1.2 GB 1.9 GB
Fits Get file →
IQ3_XXS1.3 GB 2.0 GB
Fits Get file →
IQ3_M1.4 GB 2.1 GB
Fits Get file →
Q3_K_M1.6 GB 2.2 GB
Fits Get file →
IQ4_XS1.6 GB 2.3 GB
Fits Get file →
IQ4_NL1.7 GB 2.4 GB
Fits Get file →
Q4_K_S1.8 GB 2.5 GB
Fits Get file →
Q4_K_M2.0 GB 2.7 GB
Fits Get file →
Q5_K_S2.1 GB 2.9 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 GB
Fits Get file →
Q6_K2.6 GB 3.4 GB
Fits Get file →
Q8_03.1 GB 4.0 GB
Fits Get file →
BF165.9 GB 7.1 GB
Fits Get file →

For 8 GB VRAM, use IQ4_XS (est. 2.3 GB) or Q4_K_S (est. 2.5 GB). For 12 GB VRAM, Q4_K_M (est. 2.7 GB) or Q5_K_S (est. 2.9 GB) provide better accuracy. Larger VRAM allows Q5_K_M (est. 3 GB) or Q6_K (est. 3.4 GB).

What GPU do you need for Unlimited OCR?

These figures add the file size, an fp16 KV cache at an 8K context window 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 Q8_0 (3.1 GB file, about 4.0 GB in use).
  • 6 GB VRAM: the best quant that fits is Q8_0 (3.1 GB file, about 4.0 GB in use).
  • 8 GB VRAM: the best quant that fits is BF16 (5.9 GB file, about 7.1 GB in use).

Which Unlimited OCR quant should you choose?

Q4_K_M is the usual starting point for Unlimited OCR: it balances file size and quality well. Here it is a 2.0 GB file.

The Q8_0 file is 3.1 GB, about 1.6 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.

If memory is tight, the smallest file is IQ2_M at 1.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2-ocr
Parameters2.93B

Source

Quantized bysahilchachra
FamilyUnlimited
Licensemit
Downloads (HF)16,107
Last updated2026-07-01

Frequently asked questions about Unlimited OCR

How much VRAM does Unlimited OCR need?

About 2.7 GB at Q4_K_M with an 8K context window. That is the 2.0 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 Unlimited OCR on an 8 GB GPU?

Yes, with BF16: the 5.9 GB file needs about 7.1 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of Unlimited OCR GGUF?

It depends on the quant: IQ2_M is 1.2 GB, IQ3_XXS is 1.3 GB, IQ3_M is 1.4 GB, Q3_K_M is 1.6 GB, IQ4_XS is 1.6 GB, IQ4_NL is 1.7 GB and 7 more.

Where can I download Unlimited OCR GGUF?

The files are on Hugging Face in the sahilchachra/Unlimited-OCR-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 Unlimited OCR use?

Hugging Face lists the license as mit. 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 Unlimited OCR on 8 GB VRAM?

Yes, with IQ4_XS or Q4_K_S quants, which estimate 2.3–2.5 GB VRAM usage at 8k context.

Does the model support image input?

Yes, but you must provide the shared vision projector file, which is FP16 and required for all quants.

What license applies to the model?

The model is released under the MIT license.

Other GGUFs of Unlimited-OCR

Similar models

Browse all →

More from sahilchachra

All by sahilchachra →

More Unlimited models

All Unlimited →

Other tiny models

All tiny models →