intel/neural-compressor
SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime
2.7k
Stars
330
Forks
59.7
Radar Score
Stable
Momentum
Scoring Breakdown
Impact80.1
Velocity38.0
Health57.4
Growth Metrics
7-Day Stars
+0
30-Day Stars
+0
Acceleration
1.00x
Language
Python
Why it ranks
Steady growth — consistently collecting stars and contributors.