On-Device ML Optimization
CommunityShip faster on-device ML with compact models.
Software Engineering#profiling#quantization#inference#model-optimization#coreml#neural-engine#on-device-ml
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 requiredComponents
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.
Agent Skills Search Helper
Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.