noctrex

noctrex/PaddleOCR-VL-1.5-GGUF

These are quantizations of the model PaddleOCR-VL-1.5...

Model Documentation

These are quantizations of the model PaddleOCR-VL-1.5

Download the latest llama.cpp to use them.

Try to use the best quality you can run. For the mmproj, try to use the F32 version as it will produce the best results. F32 > BF16 > F16

Includes chat template fix from https://github.com/ggml-org/llama.cpp/pull/18825

Files & Weights

FilenameSizeAction
PaddleOCR-VL-1.5-BF16.gguf 0.87 GB
PaddleOCR-VL-1.5-F16.gguf 0.87 GB
PaddleOCR-VL-1.5-Q8_0.gguf 0.46 GB
mmproj-BF16.gguf 0.82 GB
mmproj-F16.gguf 0.82 GB
mmproj-F32.gguf 1.64 GB