UN

Unlimited OCR

UnlimitedGGUF by sabafallahUpdated 2026-10-01
Download on Hugging Face
Parameters2.93B
Context—
Layers—
Architecturedeepseek2-ocr
Smallest quant2.0 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 4 quants, from 2.0 GB (Q4_K_M) to 5.9 GB (BF16).

Unlimited OCR – a 2.93B parameter OCR model in GGUF format

Unlimited OCR is a 2.93B parameter OCR model based on Deepseek2-ocr. It is available in several GGUF quantizations for llama.cpp. The model supports long‑horizon parsing and can be run with vLLM, SGLang, or Hugging Face transformers.

Good at

  • Long‑horizon OCR parsing
  • One‑shot document understanding
  • Multimodal inference with llama.cpp

Limits

  • No vision support in the base GGUF files
  • Requires CUDA 12.9 or newer for optimal performance
  • License not specified

Best for

  • Parsing large PDFs
  • Extracting structured data from documents
  • Deploying OCR in low‑latency environments

Who it’s for. Developers building OCR pipelines that need a lightweight, quantizable model. Researchers testing multimodal inference on llama.cpp or vLLM.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M2.0 GB 2.7 GB
Fits Get file →
Q5_K_M2.2 GB 3.0 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 Q4_K_M (1.95 GB file, ~2.7 GB VRAM at 8k context). For 12 GB VRAM use Q5_K_M (2.22 GB file, ~3 GB VRAM). For 16 GB VRAM use Q8_0 (3.13 GB file, ~4 GB VRAM).

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.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2-ocr
Parameters2.93B

Source

Quantized bysabafallah
FamilyUnlimited
Downloads (HF)3,984
Last updated2026-10-01

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: Q4_K_M is 2.0 GB, Q5_K_M is 2.2 GB, Q8_0 is 3.1 GB, BF16 is 5.9 GB.

Where can I download Unlimited OCR GGUF?

The files are on Hugging Face in the sabafallah/Unlimited-OCR-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

Can I run Unlimited OCR on 8 GB VRAM?

Yes, using the Q4_K_M quantization which requires about 2.7 GB VRAM at 8k context.

Does the model support vision input?

The GGUF files are for llama.cpp MTMD; vision support requires the appropriate mmproj files and the R‑SWA PR2 branch.

What is the maximum context length?

The model was trained with an unspecified context length; inference is tested at 8k tokens.

Other GGUFs of Unlimited-OCR

Similar models

Browse all →

More from sabafallah

All by sabafallah →

More Unlimited models

All Unlimited →

Other tiny models

All tiny models →