PA

PaddleOCR VL 1.6

PaddleocrGGUF by PaddlePaddleUpdated 2026-06-10
Download on Hugging Face
Parameters467M
Context128K
Layers18
Architecturepaddleocr
Smallest quant0.9 GB
Quick answer

PaddleOCR VL 1.6 needs about 1.6 GB of memory at its main file (a 0.9 GB file) with an 8K context window, so it fits on a 4 GB GPU. Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

Compact document parsing model with vision capability

PaddleOCR VL 1.6 is a 0.467 billion parameter model designed for document parsing. It supports vision tasks and is fully compatible with PaddleOCR‑VL‑1.5. The model is released under the Apache‑2.0 license.

Good at

  • Vision‑based document parsing
  • Region‑aware data optimization
  • Progressive post‑training

Limits

  • Requires vision input only
  • Large context length of 131072 tokens
  • No text‑only usage

Best for

  • OCR on scanned documents
  • Table and chart extraction
  • Complex element recognition

Who it’s for. Developers building document‑analysis applications that need a lightweight vision model. The model is suitable for integration with llama.cpp for local inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.9 GB 1.6 GB
Fits Get file →

The available GGUF file is 0.94 GB with an estimated memory usage of 1.6 GB at 8 k context. For systems with 4 GB VRAM, this quant is suitable. No other quants are provided.

What GPU do you need for PaddleOCR VL 1.6?

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: the best quant that fits is the main file (0.9 GB file, about 1.6 GB in use).

Specifications

Architecture from the GGUF header

Architecturepaddleocr
Parameters467M
Layers18
Trained context131,072 tokens
KV cache (fp16)18 KB per token

Source

Quantized byPaddlePaddle
FamilyPaddleocr
Licenseapache-2.0
Downloads (HF)93,088
Last updated2026-06-10

Frequently asked questions about PaddleOCR VL 1.6

How much VRAM does PaddleOCR VL 1.6 need?

About 1.6 GB at its main file with an 8K context window. That is the 0.9 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 PaddleOCR VL 1.6 on an 8 GB GPU?

Yes, with the smaller files: the 0.9 GB file needs about 1.6 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 GGUF?

It depends on the quant: file is 0.9 GB.

What context length does PaddleOCR VL 1.6 support?

The GGUF header lists a trained context length of 131,072 tokens (128K). The KV cache grows with the context you use: about 0.2 GB at 8K and 0.6 GB at 32K.

Where can I download PaddleOCR VL 1.6 GGUF?

The files are on Hugging Face in the PaddlePaddle/PaddleOCR-VL-1.6-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 PaddleOCR VL 1.6 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 PaddleOCR VL 1.6 on 8 GB VRAM?

Yes, the 0.94 GB GGUF file requires about 1.6 GB of VRAM at 8 k context, well within an 8 GB budget.

Does the model support text‑only inference?

No, the model is vision‑only and requires image input.

What license applies to this model?

The model is released under the Apache‑2.0 license.

Similar models

Browse all →

More from PaddlePaddle

All by PaddlePaddle →

More Paddleocr models

All Paddleocr →

Other tiny models

All tiny models →