Supported Models

The following models can be currently run through tt-torch as of Feb 3rd, 2025. Please note, there is a known bug causing incorrect output for some models. The PCC is displayed at the end of each test below. This issue will be addressed soon.

Model NameVariantPytest Command
AlbertMasked LM Basetests/models/albert/test_albert_masked_lm.py::test_albert_masked_lm[full-albert/albert-base-v2-eval]
Masked LM Largetests/models/albert/test_albert_masked_lm.py::test_albert_masked_lm[full-albert/albert-large-v2-eval]
Masked LM XLargetests/models/albert/test_albert_masked_lm.py::test_albert_masked_lm[full-albert/albert-xlarge-v2-eval]
Masked LM XXLargetests/models/albert/test_albert_masked_lm.py::test_albert_masked_lm[full-albert/albert-xxlarge-v2-eval]
Sequence Classification Basetests/models/albert/test_albert_sequence_classification.py::test_albert_sequence_classification[full-textattack/albert-base-v2-imdb-eval]
Token Classification Basetests/models/albert/test_albert_token_classification.py::test_albert_token_classification[full-albert/albert-base-v2-eval]
Autoencoder(linear)tests/models/autoencoder_linear/test_autoencoder_linear.py::test_autoencoder_linear[full-eval]
DistilBertbase uncasedtests/models/distilbert/test_distilbert.py::test_distilbert[full-distilbert-base-uncased-eval]
Llama3Btests/models/llama/test_llama_3b.py::test_llama_3b[full-meta-llama/Llama-3.2-3B-eval]
MLPMixertests/models/mlpmixer/test_mlpmixer.py::test_mlpmixer[full-eval]
MNistpytest -svv tests/models/mnist/test_mnist.py::test_mnist_train[full-eval]
MobileNet V2tests/models/MobileNetV2/test_MobileNetV2.py::test_MobileNetV2[full-eval]
TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-mobilenet_v2]
MobileNet V3Small TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-mobilenet_v3_small]
Large TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-mobilenet_v3_large]
OpenPosetests/models/openpose/test_openpose_v2.py::test_openpose_v2[full-eval]
Preciever_IOtests/models/perceiver_io/test_perceiver_io.py::test_perceiver_io[full-eval]
ResNet18tests/models/resnet/test_resnet.py::test_resnet[full-eval]
18 TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnet18]
34 TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnet34]
50tests/models/resnet50/test_resnet50.py::test_resnet[full-eval]
50 TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnet50]
101 TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnet101]
152 TorchVisiontests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnet152]
Wide ResNet50tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-wide_resnet50_2]
101tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-wide_resnet101_2]
ResNext50tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnext50_32x4d]
101_32x8dtests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnext101_32x8d]
101_64x4dtests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-resnext101_64x4d]
Regnety 400tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_400mf]
y 800tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_800mf]
y 1 6tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_1_6gf]
y 3 2tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_3_2gf]
y 8tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_8gf]
y 16tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_16gf]
y 32tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_y_32gf]
x 400tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_400mf]
x 800tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_800mf]
x 1 6tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_1_6gf]
x 3 2tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_3_2gf]
x 8tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_8gf]
x 16tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_16gf]
x 32tests/models/torchvision/test_torchvision_image_classification.py::test_torchvision_image_classification[full-regnet_x_32gf]
YoloV3tests/models/yolov3/test_yolov3.py::test_yolov3[full-eval]