PA

PaddleOCR VL 1.6

PaddleocrGGUF by mradermacherUpdated 2026-05-28
Download on Hugging Face
Parameters467M
Context128K
Layers18
Architecturepaddleocr
Smallest quant0.0 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 25 quants, from 0.0 GB to 0.4 GB (Q6_K). Longer context needs more: at 32K tokens the KV cache alone adds about 0.6 GB.

PaddleOCR VL 1.6 – compact vision‑enabled document parsing

PaddleOCR VL 1.6 is a 0.467 billion‑parameter model optimized for document parsing. It supports vision tasks and offers a 131072‑token context window. The model is released under the apache‑2.0 license.

Good at

  • High‑accuracy text, formula, and table recognition
  • Strong performance on Chinese ancient documents
  • Robust seal and stamp detection

Limits

  • No language list provided
  • Requires vision input
  • Large context size may need more VRAM

Best for

  • OCR of printed documents
  • Table extraction from PDFs
  • Recognition of rare Chinese characters

Who it’s for. Developers building OCR pipelines that need a lightweight, vision‑enabled model. The model can be dropped into existing PaddleOCR workflows with zero adaptation cost.

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
—0.0 GB 0.7 GB
Fits Get file →
IQ1_S0.2 GB 0.8 GB
Fits Get file →
IQ1_M0.2 GB 0.8 GB
Fits Get file →
IQ2_XXS0.2 GB 0.8 GB
Fits Get file →
IQ2_XS0.2 GB 0.8 GB
Fits Get file →
IQ2_S0.2 GB 0.9 GB
Fits Get file →
IQ2_M0.2 GB 0.9 GB
Fits Get file →
Q2_K_S0.2 GB 0.9 GB
Fits Get file →
IQ3_XXS0.2 GB 0.9 GB
Fits Get file →
Q2_K0.2 GB 0.9 GB
Fits Get file →
IQ3_XS0.2 GB 0.9 GB
Fits Get file →
Q3_K_S0.2 GB 0.9 GB
Fits Get file →
IQ3_S0.2 GB 0.9 GB
Fits Get file →
IQ3_M0.3 GB 0.9 GB
Fits Get file →
Q3_K_M0.3 GB 0.9 GB
Fits Get file →
Q3_K_L0.3 GB 0.9 GB
Fits Get file →
IQ4_XS0.3 GB 0.9 GB
Fits Get file →
Q4_00.3 GB 0.9 GB
Fits Get file →
IQ4_NL0.3 GB 0.9 GB
Fits Get file →
Q4_K_S0.3 GB 0.9 GB
Fits Get file →
Q4_K_M0.3 GB 1.0 GB
Fits Get file →
Q4_10.3 GB 1.0 GB
Fits Get file →
Q5_K_S0.3 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 →

For 8 GB VRAM, use IQ1_S (0.16 GB) or IQ1_M (0.17 GB). For 12 GB VRAM, IQ2_S (0.20 GB) or Q2_K_S (0.21 GB) are suitable. If 16 GB VRAM is available, Q4_K_M (0.30 GB) or Q5_K_S (0.34 GB) provide higher quality while staying within memory limits.

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 Q6_K (0.4 GB file, about 1.0 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.

If memory is tight, the smallest file is the first one in the table at 0.0 GB, with the quality trade-offs that come with fewer bits.

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 bymradermacher
FamilyPaddleocr
Licenseapache-2.0
Downloads (HF)871
Last updated2026-05-28

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 Q6_K: the 0.4 GB file needs about 1.0 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 0.0 GB, IQ1_S is 0.2 GB, IQ1_M is 0.2 GB, IQ2_XXS is 0.2 GB, IQ2_XS is 0.2 GB, IQ2_S is 0.2 GB and 19 more.

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 mradermacher/PaddleOCR-VL-1.6-i1-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 IQ1_S and IQ1_M quantizations are under 0.2 GB, which fits 8 GB VRAM with room for context and runtime overhead.

Does the model support English text only?

No, the model supports multiple languages, but the language list is not specified in the provided data.

Is the model compatible with PaddleOCR‑VL‑1.5?

Yes, the architecture is fully compatible, allowing zero‑cost plug‑and‑play migration from PaddleOCR‑VL‑1.5.

Other GGUFs of PaddleOCR-VL-1.6

Similar models

Browse all →

More from mradermacher

All by mradermacher →

More Paddleocr models

All Paddleocr →

Other tiny models

All tiny models →