NC
neural-compressor
70.5
Moderate
High confidence
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
Pillar Breakdown
Adoption
35%
61.0
Maintenance
30%
80.3
Friction
20%
98.3
Ecosystem
15%
54.7
Momentum
0.76Surging
7d change -0.32
High confidenceIn Model Optimization
Ranked #9 of 17