On-Device ML Optimization

Community

Ship faster on-device ML with compact models.

Authormelissa-pereira-deel
Version1.0.0
Installs0

System Documentation

What problem does it solve?

Shipping on-device ML models that run fast and fit within constraints on modern devices. This includes CoreML/MLX conversions, quantization, and Neural Engine considerations to reduce latency, memory usage, and energy draw.

Core Features & Use Cases

  • On-device optimization for speed, size, and energy efficiency.
  • Use cases include mobile apps, edge devices, and offline inference with streaming support.
  • Real-world example: tailoring a vision model to run at real-time frame rates on iPhone hardware.

Quick Start

Profile your model on target devices and apply quantization, palettization, and compute-unit tuning to meet Neural Engine constraints.

Dependency Matrix

Required Modules

None required

Components

Standard package

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: On-Device ML Optimization
Download link: https://github.com/melissa-pereira-deel/creative-technologist-agent/archive/main.zip#on-device-ml-optimization

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.