PA

PaddleOCR VL 1.6 Bangla

PaddleocrGGUF by hasanmdsadadulUpdated 2026-09-29
Download on Hugging Face
Parameters6M
Context—
Layers—
Architecturepaddleocr
Smallest quant0.0 GB
Quick answer

PaddleOCR VL 1.6 Bangla needs about 0.5 GB of memory at its main file (a 0.0 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 2 quants, from 0.0 GB to 0.9 GB.

Bangla fine‑tuned PaddleOCR‑VL‑1.6 for printed documents

PaddleOCR‑VL‑1.6 Bangla is a fine‑tune of PaddleOCR‑VL‑1.6 for printed Bangla and English documents. It achieves under 1% character error on held‑out printed words and 0.15% on full‑page Bangla pages. The model is a drop‑in replacement for the base model.

Good at

  • Accurate printed Bangla OCR
  • Full‑page reading with bounding boxes
  • Low character error on synthetic test sets

Limits

  • Handwriting error rate about 31%
  • Isolated real‑world words error about 10%
  • Requires verification of extracted figures

Best for

  • Printed Bangla invoices
  • Form and statement extraction
  • Book and letter digitisation

Who it’s for. Users needing reliable OCR for printed Bangla and English documents. It is suitable for businesses processing invoices, forms, and other scanned paperwork.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.5 GB
Fits Get file →
—0.9 GB 1.5 GB
Fits Get file →

The 0.02 GB GGUF file uses about 0.5 GB of VRAM at 8 k context and is ideal for 8 GB VRAM setups. The 0.94 GB file uses about 1.5 GB of VRAM and is suitable for 12 GB or larger VRAM systems.

What GPU do you need for PaddleOCR VL 1.6 Bangla?

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 the main file (0.9 GB file, about 1.5 GB in use).

Specifications

Architecture from the GGUF header

Architecturepaddleocr
Parameters6M

Source

Quantized byhasanmdsadadul
FamilyPaddleocr
Downloads (HF)361
Last updated2026-09-29

Frequently asked questions about PaddleOCR VL 1.6 Bangla

How much VRAM does PaddleOCR VL 1.6 Bangla need?

About 0.5 GB at its main file with an 8K context window. That is the 0.0 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 PaddleOCR VL 1.6 Bangla on an 8 GB GPU?

Yes, with the smaller files: the 0.9 GB file needs about 1.5 GB at 8K context. Larger quants in this repository do not fit in 8 GB.

What is the file size of PaddleOCR VL 1.6 Bangla GGUF?

It depends on the quant: file is 0.0 GB, file is 0.9 GB.

Where can I download PaddleOCR VL 1.6 Bangla GGUF?

The files are on Hugging Face in the hasanmdsadadul/PaddleOCR-VL-1.6-Bangla repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does PaddleOCR VL 1.6 Bangla use?

Hugging Face lists the license as cc-by-sa-4.0. 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 this model on 8 GB VRAM?

Yes, the 0.02 GB GGUF file requires approximately 0.5 GB of VRAM at 8 k context, fitting within an 8 GB VRAM budget.

Does this model support handwritten text?

No, handwriting has a character error rate of about 31% and is not recommended.

Is the model compatible with PaddleOCR‑VL‑1.5?

Yes, the architecture is fully compatible and can be used as a drop‑in replacement.

Other GGUFs of PaddleOCR-VL-1.6

Similar models

Browse all →

More Paddleocr models

All Paddleocr →

Other tiny models

All tiny models →