{"categories":[{"label":"Software Development","url":"https://skillfed.io/packages/category/software-development/14"},{"label":"Libraries","url":"https://skillfed.io/packages/category/software-development-libraries/8"},{"label":"Scientific/Engineering","url":"https://skillfed.io/packages/category/scientific-engineering/6"},{"label":"Python Modules","url":"https://skillfed.io/packages/category/software-development-libraries-python-modules/17"},{"label":"Artificial Intelligence","url":"https://skillfed.io/packages/category/scientific-engineering-artificial-intelligence/8"},{"label":"Mathematics","url":"https://skillfed.io/packages/category/scientific-engineering-mathematics/3"}],"enrichment":{"capability":"Quantizes LiteRT models to reduce size and improve inference performance on edge devices, supporting dynamic, weight-only, and static quantization strategies with configurable recipes.","skillfed_tags":["model-compression","edge-ml","quantization"],"use_cases":["Reduce model size and memory footprint for deployment on mobile and embedded devices without calibration data using dynamic quantization.","Optimize inference latency on NPU hardware by applying static quantization with calibration on representative data.","Selectively quantize specific operators or layers while keeping others in FP32 to balance quality and performance.","Convert GenAI and large language models to 4-bit or 8-bit weight quantization for on-device inference.","Experiment with mixed-precision quantization strategies to find the optimal trade-off between model size and accuracy."],"what_it_does":"AI Edge Quantizer is a tool for converting unquantized LiteRT models into quantized versions optimized for edge device deployment. It targets advanced developers working with resource-constrained environments, particularly for GenAI and large language models. The package provides three quantization strategies: dynamic quantization (weights quantized, activations remain float, no calibration needed), weight-only quantization (reduced model size with float computation), and static quantization (both weights and activations quantized, requires calibration data). Users define quantization behavior through recipes that specify which operators to quantize, bit-widths, symmetry, and granularity settings.\n\nThe workflow is straightforward: instantiate a Quantizer with an input .tflite file, load a quantization recipe (either from built-in templates or custom-defined), then quantize and export. The package depends on numpy, scipy, absl-py for core functionality, plus Google's ai-edge-litert and litert-lm-builder for LiteRT model handling. It supports Python 3.10\u20133.13 on Linux and macOS, with active maintenance and nightly releases.","worth_installing":"Yes, if you are quantizing LiteRT models for edge deployment. The package is actively maintained, has low install friction, carries a permissive license, and provides a clear API with multiple quantization strategies. No known vulnerabilities. Best suited for advanced developers; requires understanding of quantization trade-offs and model format requirements. Start with dynamic quantization recipes if you lack calibration data."},"id":"ai-edge-quantizer","links":{"html":"https://skillfed.io/packages/ai-edge-quantizer","md":"https://skillfed.io/packages/ai-edge-quantizer.md","pypi":"https://pypi.org/project/ai-edge-quantizer/"},"maintenance":{"status":"active"},"meta":{"latest_release":"2026-07-13","license_spdx":"Apache-2.0","license_treatment":"permissive","name":"ai-edge-quantizer","python_support":"supports_current","summary":"A quantizer for advanced developers to quantize converted AI Edge models."},"popularity":{"monthly_downloads":169674,"position":10410,"tier":"top_15000"},"security":{"n_vulnerabilities":0},"version":"0.8.0"}