This repo contains a variety of different, representative example models in the Quantized ONNX model format.
| Model Name / Link | Dataset | Accuracy / Top-1 | NN Topology | Dominant Quantization | More Details |
|---|---|---|---|---|---|
| KWS MLP w3a3 | GSCV2 | 87.89% | MLP | int3 weights / int3 activations | README |
| LFC_1W1A | MNIST | 98.88% | MLP | bipolar weights / bipolar activations | README |
| CNV_1W1A | CIFAR-10 | 84.22% | VGG10-like | bipolar weights / bipolar activations | README |
| CNV_1W1A | GTSRB | 96.93% | VGG10-like | bipolar weights / bipolar activations | README |
| mobilenet_4W4A | ImageNet | 71.14% | MobileNet-v1 | int4 weights / int4 activations | README |
| unsw_nb15_mlp_w2a2 | UNSW-NB15 | 91.90% | MLP | int2 weights / int2 activations | README |
| quant_resnet18_w4a4_a2q_16b | CIFAR10 | 94.2% | ResNet-18 | int4 weights / uint4 activations (int16 accumulators) | README |
| ResNet-8 | CIFAR100 | 70.12% | ResNet-8 | int3 weights / int3 activations | README |
| qkeras_jettagging | LHC jets | 76.2% | MLP | 6b weights / 6b activations | README |
| ResNet18 8w8a_e4m3 | CIFAR10 | 93.09% | ResNet-18 | FP8 E4M3 | README |
Note: This table is incomplete. For a full list of models, see the models directory on GitHub.