Intel Neural Compressor
Open-source Python library that automates model quantization, pruning and distillation across PyTorch, TensorFlow and ONNX Runtime to speed inference on Intel hardware.
Find alternatives to Intel Neural Compressor
Free and open source, distributed via GitHub, PyPI and Intel's AI Tools Selector.
What it does
- Model inference
Sources
- Pricing
- Sold within
-
Intel's own page states "A stand-alone download of Intel Neural Compressor is available. You can download binaries from Intel or choose your preferred repository" and links an "Open Source Version (GitHub)"; no price is stated. The page also offers it bundled in the AI Tools Selector suite, but the stand-alone route is explicit and free.
Also from Intel
-
Intel AI Playground Application
Free local generative-AI desktop app for Intel AI PCs offering offline chat, image generation and editing, and video generation using open models.
-
Intel Gaudi AI Accelerator Hardware
AI training and inference accelerator sold as PCIe cards and OEM systems.
-
Intel Geti Platform
Computer-vision development platform providing AI-assisted annotation, active learning and model training for classification, detection and segmentation.
-
OpenVINO toolkit Developer tool
Open-source toolkit that optimises and runs trained models across Intel CPUs, GPUs and NPUs.
-
Intel Tiber AI Cloud Infrastructure service
Cloud platform offering pay-as-you-go bare-metal and virtual access to Intel Gaudi accelerators, Max Series GPUs and Xeon CPUs for AI training and inference.
Something wrong here? Send a correction — quote this product id: intel-neural-compressor.