PA

PaddleOCR VL 1.6

PaddleocrGGUF by SanjeevSOLANKIUpdated 2026-06-25
Download on Hugging Face
Parameters467M
Context128K
Layers18
Architecturepaddleocr
Smallest quant0.3 GB
Quick answer

PaddleOCR VL 1.6 needs about 1.0 GB of memory at Q4_K_M (a 0.3 GB file) with an 8K context window, so it fits on a 4 GB GPU. This repository has 4 quants, from 0.3 GB (Q4_K_M) to 0.5 GB (Q8_0). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

Compact vision‑language OCR model for document parsing

PaddleOCR‑VL‑1.6 is a 0.467 billion‑parameter vision‑language model designed for efficient document OCR. It integrates a NaViT visual encoder with an ERNIE‑4.5‑0.3B language model and supports 109 languages. The model is available in several GGUF quantizations for llama.cpp.

Good at

  • Document OCR
  • Multilingual text recognition
  • Table and formula extraction

Limits

  • No text‑only inference
  • Requires mmproj file
  • Limited to 131072 context tokens

Best for

  • Local OCR on edge devices
  • Batch document processing
  • Real‑time form extraction

Who it’s for. Developers needing a lightweight OCR solution that can run locally with llama.cpp. The model is suitable for applications that require multilingual document parsing and low‑resource inference.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
Q4_K_M0.3 GB 1.0 GB
Fits Get file →
Q5_K_M0.3 GB 1.0 GB
Fits Get file →
Q6_K0.4 GB 1.0 GB
Fits Get file →
Q8_00.5 GB 1.1 GB
Fits Get file →

For 8 GB VRAM, use Q4_K_M (0.3 GB file, ~1 GB memory). If 12 GB VRAM is available, Q5_K_M (0.34 GB) or Q6_K (0.39 GB) are viable. For the highest precision on 16 GB VRAM, Q8_0 (0.5 GB) can be used.

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 Q8_0 (0.5 GB file, about 1.1 GB in use).

Which PaddleOCR VL 1.6 quant should you choose?

Q4_K_M is the usual starting point for PaddleOCR VL 1.6: it balances file size and quality well. Here it is a 0.3 GB file.

The Q8_0 file is 0.5 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

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

Source

Quantized bySanjeevSOLANKI
FamilyPaddleocr
Licenseapache-2.0
Downloads (HF)1,723
Last updated2026-06-25

Frequently asked questions about PaddleOCR VL 1.6

How much VRAM does PaddleOCR VL 1.6 need?

About 1.0 GB at Q4_K_M 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 1.6 on an 8 GB GPU?

Yes, with Q8_0: the 0.5 GB file needs about 1.1 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: Q4_K_M is 0.3 GB, Q5_K_M is 0.3 GB, Q6_K is 0.4 GB, Q8_0 is 0.5 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 SanjeevSOLANKI/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 Q4_K_M quant uses 0.3 GB file size and requires about 1 GB memory at 8 k context, fitting comfortably in 8 GB VRAM.

Does this model support text‑only prompts?

No, PaddleOCR‑VL is a vision model and requires an image input; text‑only prompts are out of distribution.

What license applies to the GGUF files?

The GGUF files are redistributed under Apache‑2.0, the same license as the original PaddlePaddle model.

Other GGUFs of PaddleOCR-VL

Similar models

Browse all →

More Paddleocr models

All Paddleocr →

Other tiny models

All tiny models →