nougat-small-onnx-quant_avx2

This was quantized from pszemraj/nougat-small-onnx using the --avx2 flag so should work properly on most machines.

per_channel is set to True for better accuracy
Usage is the same as: https://huggingface.co/pszemraj/nougat-small-onnx

Inference Providers NEW

This model is not currently available via any of the supported Inference Providers.

Collection including pszemraj/nougat-small-onnx-quant_avx2