PA

PaddleOCR VL half

PaddleocrGGUF by LiyulingyueUpdated 2025-11-10
Download on Hugging Face
Parameters467M
Context128K
Layers18
Architectureernie4_5
Smallest quant0.3 GB
Quick answer

PaddleOCR VL half needs about 1.0 GB of memory at its main file (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 5 quants, from 0.3 GB (Q4_0) to 0.9 GB. Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

PaddleOCR VL half is a 467M-parameter Paddleocr model in GGUF format, quantized by Liyulingyue. Its trained context length is 128K tokens. The repository has 5 quant files, from 0.3 GB (Q4_0) to 0.9 GB.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_00.3 GB 0.9 GB
Fits Get file →
—0.3 GB 1.0 GB
Fits Get file →
—0.3 GB 1.0 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →
—0.9 GB 1.6 GB
Fits Get file →

What GPU do you need for PaddleOCR VL half?

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).

Which PaddleOCR VL half quant should you choose?

If memory is tight, the smallest file is Q4_0 at 0.3 GB, with the quality trade-offs that come with fewer bits. The usual sweet spot between file size and quality, and the quant most people start with.

New to quant names? Read GGUF quantization explained.

Specifications

Architecture from the GGUF header

Architectureernie4_5
Parameters467M
Layers18
Trained context131,072 tokens
KV cache (fp16)18 KB per token

Source

Quantized byLiyulingyue
FamilyPaddleocr
Licenseapache-2.0
Downloads (HF)163
Last updated2025-11-10

Frequently asked questions about PaddleOCR VL half

How much VRAM does PaddleOCR VL half need?

About 1.0 GB at its main file with an 8K context window. That is the 0.3 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 half 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 half GGUF?

It depends on the quant: Q4_0 is 0.3 GB, file is 0.3 GB, file is 0.3 GB, Q8_0 is 0.5 GB, file is 0.9 GB.

What context length does PaddleOCR VL half 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 half GGUF?

The files are on Hugging Face in the Liyulingyue/PaddleOCR-VL-half-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 half 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.

Other GGUFs of PaddleOCR-VL

Similar models

Browse all →

More from Liyulingyue

All by Liyulingyue →

More Paddleocr models

All Paddleocr →

Other tiny models

All tiny models →