PA

paddle ocr vl 1.5 lmk

PaddleGGUF by lm-kitUpdated 2026-08-11
Download on Hugging Face
Parameters467M
Context128K
Layers18
Architecturepaddleocr
Smallest quant0.9 GB
Quick answer

paddle ocr vl 1.5 lmk needs about 1.6 GB of memory at F16 (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.

paddle ocr vl 1.5 lmk is a 467M-parameter Paddle model in GGUF format, quantized by lm-kit. Its trained context length is 128K tokens. The repository has 1 quant file, from 0.9 GB (F16) to 0.9 GB (F16).

Quants & memory

QuantFileEst. memoryvs VRAMResultDownload
F160.9 GB 1.6 GB
Fits Get file →

What GPU do you need for paddle ocr vl 1.5 lmk?

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 F16 (0.9 GB file, about 1.6 GB in use).

Which paddle ocr vl 1.5 lmk quant should you choose?

F16 (0.9 GB) is the middle option in this repository. The unquantized model. It gives original quality and needs the most memory, so it is mainly for conversion or reference.

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 bylm-kit
FamilyPaddle
Licenseapache-2.0
Downloads (HF)39
Last updated2026-08-11

Frequently asked questions about paddle ocr vl 1.5 lmk

How much VRAM does paddle ocr vl 1.5 lmk need?

About 1.6 GB at F16 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 paddle ocr vl 1.5 lmk on an 8 GB GPU?

Yes, with F16: 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 paddle ocr vl 1.5 lmk GGUF?

It depends on the quant: F16 is 0.9 GB.

What context length does paddle ocr vl 1.5 lmk 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 paddle ocr vl 1.5 lmk GGUF?

The files are on Hugging Face in the lm-kit/paddle-ocr-vl-1.5-lmk repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.

What license does paddle ocr vl 1.5 lmk 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.

Similar models

Browse all →

More from lm-kit

All by lm-kit →

More Paddle models

All Paddle →

Other tiny models

All tiny models →