Nuqta Arabic OCR 4B needs about 4.6 GB of memory at Q4_K_M (a 2.9 GB file) with an 8K context window, so it fits on a 6 GB GPU. This repository has 2 quants, from 2.9 GB (Q4_K_M) to 4.8 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 4.7 GB.
Nuqta Arabic OCR 4B – offline Arabic OCR in GGUF format
Nuqta Arabic OCR 4B is an open‑weights Arabic OCR model that converts scans, photos and PDFs into clean text or Markdown with HTML tables. It preserves printed tashkeel and delivers high accuracy on tables, IDs and passports.
Good at
- High OCR accuracy on Arabic documents
- Faithful tashkeel preservation
- Table extraction as HTML
Limits
- Requires 16 GB GPU for bf16, 6 GB RAM at 4‑bit
- No vision support beyond OCR
- License is Apache‑2.0
Best for
- Offline OCR on laptops
- Batch processing of Arabic PDFs
- Extracting structured data from forms
Who it’s for. Developers and organizations needing on‑premises Arabic OCR without sending data to the cloud. Suitable for privacy‑sensitive document workflows.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q4_K_M | 2.9 GB | 4.6 GB | Fits | Get file → | |
| Q8_0 | 4.8 GB | 6.5 GB | Fits | Get file → |
For 8 GB VRAM use Q4_K_M (2.9 GB file, ~4.6 GB RAM at 8k context). For 12 GB VRAM use Q8_0 (4.84 GB file, ~6.5 GB RAM at 8k context).
What GPU do you need for Nuqta Arabic OCR 4B?
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: no quant fits at an 8K context.
- 6 GB VRAM: the best quant that fits is Q4_K_M (2.9 GB file, about 4.6 GB in use).
- 8 GB VRAM: the best quant that fits is Q8_0 (4.8 GB file, about 6.5 GB in use).
Which Nuqta Arabic OCR 4B quant should you choose?
Q4_K_M is the usual starting point for Nuqta Arabic OCR 4B: it balances file size and quality well. Here it is a 2.9 GB file.
The Q8_0 file is 4.8 GB, about 1.7 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
Source
Frequently asked questions about Nuqta Arabic OCR 4B
How much VRAM does Nuqta Arabic OCR 4B need?
About 4.6 GB at Q4_K_M with an 8K context window. That is the 2.9 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 Nuqta Arabic OCR 4B on an 8 GB GPU?
Yes, with Q8_0: the 4.8 GB file needs about 6.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.
What is the file size of Nuqta Arabic OCR 4B GGUF?
It depends on the quant: Q4_K_M is 2.9 GB, Q8_0 is 4.8 GB.
What context length does Nuqta Arabic OCR 4B 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 4.7 GB at 32K.
Where can I download Nuqta Arabic OCR 4B GGUF?
The files are on Hugging Face in the SalahALHaismawi/Nuqta-Arabic-OCR-4B-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 Nuqta Arabic OCR 4B 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 Nuqta Arabic OCR 4B on 8 GB VRAM?
Yes, the Q4_K_M quantization uses 2.9 GB file size and requires about 4.6 GB RAM at 8k context, fitting within 8 GB VRAM.
Does the model support image input?
Yes, it processes images of Arabic documents and outputs text or Markdown with tables.
What license applies?
The model is released under the Apache‑2.0 license, allowing free use and modification.