Examples

December 24, 2025 · View on GitHub

Intel® Neural Compressor validated examples with multiple compression techniques, including quantization, pruning, knowledge distillation and orchestration.

PyTorch Examples

Quantization

Model Domain Method Examples
deepseek-ai/DeepSeek-R1 Natural Language Processing Quantization (MXFP8/MXFP4/NVFP4) link
Qwen/Qwen3-235B-A22B Natural Language Processing Quantization (MXFP8/MXFP4) link
Framepack Image + Text to Video Quantization (MXFP8/FP8) link
FLUX.1-dev Text to Image Quantization (MXFP8/FP8) link
Llama-4-Scout-17B-16E-Instruct Multimodal Modeling Quantization (MXFP4) link
Llama-3.1-8B-Instruct Natural Language Processing Mixed Precision (MXFP4+MXFP8) link
Quantization (MXFP4/MXFP8/NVFP4) link
Llama-3.1-70B-Instruct Natural Language Processing
Quantization (MXFP8/NVFP4/uNVFP4) link
Llama-3.3-70B-Instruct Natural Language Processing Mixed Precision (MXFP4+MXFP8) link
Quantization (MXFP4/MXFP8/NVFP4) link
gpt_j Natural Language Processing Weight-Only Quantization link
Static Quantization (IPEX) link
llama2_7b Natural Language Processing Weight-Only Quantization link
Static Quantization (IPEX) link
opt_125m Natural Language Processing Static Quantization (IPEX) link
Static Quantization (PT2E) link
Weight-Only Quantization link
resnet18 Image Recognition Mixed Precision link
Static Quantization link

TensorFlow Examples

Quantization

Model Domain Method Examples
bert_large_squad_model_zoo Natural Language Processing Post-Training Static Quantization link
transformer_lt Natural Language Processing Post-Training Static Quantization link
inception_v3 Image Recognition Post-Training Static Quantization link
mobilenetv2 Image Recognition Post-Training Static Quantization link
resnetv2_50 Image Recognition Post-Training Static Quantization link
vgg16 Image Recognition Post-Training Static Quantization link
ViT Image Recognition Post-Training Static Quantization link
GraphSage Graph Networks Post-Training Static Quantization link
yolo_v5 Object Detection Post-Training Static Quantization link
faster_rcnn_resnet50 Object Detection Post-Training Static Quantization link
mask_rcnn_inception_v2 Object Detection Post-Training Static Quantization link
ssd_mobilenet_v1 Object Detection Post-Training Static Quantization link
wide_deep_large_ds Recommendation Post-Training Static Quantization link
3dunet-mlperf Semantic Image Segmentation Post-Training Static Quantization link