UN

baidu.Unlimited OCR

UnlimitedGGUF by DevQuasarUpdated 2026-06-25
Download on Hugging Face
Parameters2.93B
Context—
Layers—
Architecturedeepseek2-ocr
Smallest quant1.6 GB
Quick answer

baidu.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 5 quants, from 1.6 GB (Q3_K_M) to 3.1 GB (Q8_0).

baidu.Unlimited OCR – a 2.93B parameter OCR model

baidu.Unlimited OCR is a 2.93B parameter OCR model based on the deepseek2-ocr architecture. It supports one‑shot long‑horizon parsing and runs on NVIDIA GPUs with Hugging Face transformers, vLLM, or SGLang. The model is available in several GGUF quantizations.

Good at

  • One‑shot long‑horizon OCR
  • High‑accuracy text extraction
  • Fast inference on GPUs

Limits

  • No vision support in the text prompt
  • Context length limited to 8k tokens
  • License information not provided

Best for

  • OCR on scanned documents
  • PDF text extraction
  • Batch text recognition

Who it’s for. Developers building OCR pipelines that require fast, GPU‑accelerated inference. The model is suitable for applications needing high‑accuracy text extraction from images or PDFs.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q3_K_M1.6 GB 2.2 GB
Fits Get file →
Q4_K_M2.0 GB 2.7 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 →

For an 8 GB VRAM budget, use the Q3_K_M quantization (1.55 GB file, ~2.2 GB memory at 8k context). If more memory is available, Q4_K_M (1.95 GB, ~2.7 GB) or Q5_K_M (2.22 GB, ~3 GB) can be used for higher precision. The Q6_K and Q8_0 options require more than 3 GB of VRAM.

What GPU do you need for baidu.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).

Which baidu.Unlimited OCR quant should you choose?

Q4_K_M is the usual starting point for baidu.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 Q3_K_M at 1.6 GB, with the quality trade-offs that come with fewer bits. A reasonable choice when a 4-bit file will not fit, mostly on larger models. Quality loss is noticeable but often acceptable.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architecturedeepseek2-ocr
Parameters2.93B

Source

Quantized byDevQuasar
FamilyUnlimited
Downloads (HF)2,008
Last updated2026-06-25

Frequently asked questions about baidu.Unlimited OCR

How much VRAM does baidu.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 baidu.Unlimited OCR on an 8 GB GPU?

Yes, with Q8_0: the 3.1 GB file needs about 4.0 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of baidu.Unlimited OCR GGUF?

It depends on the quant: Q3_K_M is 1.6 GB, Q4_K_M is 2.0 GB, Q5_K_M is 2.2 GB, Q6_K is 2.6 GB, Q8_0 is 3.1 GB.

Where can I download baidu.Unlimited OCR GGUF?

The files are on Hugging Face in the DevQuasar/baidu.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 baidu.Unlimited OCR on 8 GB VRAM?

Yes, the Q3_K_M quantization requires about 2.2 GB of VRAM at 8k context, which fits within an 8 GB GPU.

Which inference framework is easiest to set up?

Hugging Face transformers on NVIDIA GPUs is the most straightforward, with tested support for CUDA12.9.

Does the model support PDF input directly?

PDFs can be converted to images using PyMuPDF and then processed; the model itself handles image‑to‑text conversion.

Other GGUFs of Unlimited-OCR

Similar models

Browse all →

More from DevQuasar

All by DevQuasar →

More Unlimited models

All Unlimited →

Other tiny models

All tiny models →