intel/neural-compressor

neural-compressor

✅ Recently maintained

SOTA low-bit LLM quantization (INT8/FP8/MXFP8/INT4/MXFP4/NVFP4) & sparsity; leading model compression techniques on PyTorch, TensorFlow, and ONNX Runtime

2,729Stars
332Forks
+47-day stars

Python · Apache-2.0 · Last push 2026-10-30

Official repository & installation ↗
low-precisionpruningsparsityauto-tuningknowledge-distillationquantizationquantization-aware-trainingpost-training-quantizationsmoothquantlarge-language-models

Star history

2025-09-292026-11-02
View historical data
DateStars
2026-10-042,710
2026-10-052,710
2026-10-062,710
2026-10-072,710
2026-10-082,710
2026-10-092,710
2026-10-102,710
2026-10-112,710
2026-10-122,710
2026-10-132,711
2026-10-142,711
2026-10-152,711
2026-10-162,717
2026-10-172,718
2026-10-182,721
2026-10-192,721
2026-10-202,721
2026-10-212,722
2026-10-222,722
2026-10-232,722
2026-10-242,722
2026-10-252,724
2026-10-262,727
2026-10-272,728
2026-10-282,728
2026-10-292,729
2026-10-302,729
2026-10-312,729
2026-11-012,729
2026-11-022,729

Get the project

git clone https://github.com/intel/neural-compressor.git

Related projects & alternative candidates

Related domains do not imply feature parity. Review official documentation and licenses.

langfuse

🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.

★ 36,857linux

The Linux kernel source tree, the core of the operating system, worth studying.

★ 254,098FreeDomain

Free domain registration plus practical DNS learning resources for anyone new to domains.

★ 206,748