PaddleOCR-VL-1.5 — 4-bit (MLX)
A 4-bit, group-size-64 MLX quantization of
PaddlePaddle/PaddleOCR-VL-1.5, for
on-device OCR on Apple Silicon. The newer
PaddleOCR-VL-1.6 is an architecture-identical
drop-in successor — this 1.5 quant is kept for reference.
| Base model | PaddlePaddle/PaddleOCR-VL-1.5 |
| Quantization | 4-bit, group size 64, affine |
| Format | MLX safetensors |
| Size | ~0.7 GB |
License & attribution
Apache-2.0, inherited from the base model. All credit for the model goes to the PaddlePaddle / PaddleOCR team — this repository only provides an MLX-quantized copy.
- Downloads last month
- 49
Model size
0.3B params
Tensor type
BF16
·
U32 ·
Hardware compatibility
Log In to add your hardware
4-bit
Model tree for huggingfinger0/PaddleOCR-VL-1.5-4bit
Base model
baidu/ERNIE-4.5-0.3B-Paddle Finetuned
PaddlePaddle/PaddleOCR-VL-1.5