ScriptAI Infrastructurev1.2

Edge Model Optimization

by Community · free · Last verified 2026-03-17

Optimizes PyTorch and TensorFlow models for edge hardware by applying INT8/FP16 quantization and converting them to ONNX or TFLite formats. This script provides platform-specific tuning for ARM and NPU targets, benchmarking latency and memory usage while generating a report on accuracy trade-offs.

https://github.com/NVIDIA/TensorRT ↗

C+

C+—Average

Adoption: BQuality: AFreshness: ACitations: C+Engagement: F

Specifications

License: Apache-2.0
Pricing: free
Capabilities: INT8 post-training quantization, FP16 quantization, ONNX model export and validation, TensorFlow Lite (TFLite) conversion, Hardware-specific tuning for ARM and NPU targets, Latency and memory footprint benchmarking, Model accuracy degradation analysis, Automated deployment report generation
Integrations: PyTorch, TensorFlow, ONNX, ONNX Runtime, TensorFlow Lite
Use Cases: [object Object], [object Object], [object Object], [object Object], [object Object]
API Available: No
Language: python
Dependencies: torch, onnx, onnxruntime, tensorflow-lite-runtime, numpy
Environment: Python 3.10+
Est. Runtime: 5-30 minutes per model
Tags: edge-deployment, onnx, quantization, tflite, model-compression, model-optimization, embedded-ml, tinyml, pytorch, tensorflow, arm-processors, npu
Added: 2026-03-17
Completeness: 0.9%

Index Score

58.7

Adoption

Quality

Freshness

Citations

Engagement

Need this tool deployed for your team?

Get a Custom Setup

Explore the full AI ecosystem on Agents as a Service