skills.rest
tuliopc23
tuliopc23COMMUNITY
Explore all skills by this author →
Website𝕏@tuliopinheiro_GitHub

coreml

Convert and compress PyTorch models to CoreML for Apple devices.

Updated Dec 3, 2025
Search Tags:#machine learning#model optimization#coreml#on-device ai#llm inference#pytorch conversion
One-click install
npx skills add https://github.com/tuliopc23/flying-dutchman-app --skill coreml-tuliopc23
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: coreml
Source: https://github.com/tuliopc23/flying-dutchman-app/tree/main/.claude/skills/axiom-ios-ml/coreml
Command: npx skills add https://github.com/tuliopc23/flying-dutchman-app --skill coreml-tuliopc23

SYSTEM DOCUMENTATION & REQUIREMENTS

💡 This Skill includes references (resource) components.

What problem does it solve?

This Skill enables the deployment and optimization of custom machine learning models directly on Apple devices, ensuring privacy, performance, and offline capabilities.

Core Features & Use Cases

  • Model Conversion: Convert models from frameworks like PyTorch to CoreML format.
  • Optimization: Compress models using techniques like palettization and quantization to reduce size and improve inference speed.
  • LLM Inference: Implement efficient on-device inference for Large Language Models.
  • Stateful Models: Handle models with internal state, such as KV-caches for transformers.
  • Use Case: Convert a custom image classification model trained in PyTorch to CoreML, compress it to fit within app size limits, and integrate it for real-time on-device predictions.

Quick Start

Use the coreml skill to convert the attached PyTorch model 'my_model.pt' to CoreML format, targeting iOS 18.

Frequently Asked Questions about coreml

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I convert a PyTorch model to CoreML format for iOS?▼

You can convert a PyTorch model to CoreML format by using CoreML tools to translate the trained model, enabling direct deployment and real-time predictions on Apple devices like iOS.

What is the best way to compress a machine learning model for on-device inference?▼

Compressing a machine learning model for on-device inference involves applying techniques like palettization and quantization to reduce model size and improve inference speed on Apple devices.

Can I run Large Language Model inference efficiently on macOS and iOS?▼

Yes, you can run Large Language Model inference efficiently on macOS and iOS by using CoreML tools that support stateful model execution, KV-cache management for transformers, and efficient MLTensor operations.

Does CoreML support stateful models with KV-cache management for transformers?▼

Yes, CoreML supports stateful models with KV-cache management for transformers, enabling efficient handling of internal state and tensor operations during on-device LLM inference.

How does MLTensor work for efficient tensor operations on Apple devices?▼

MLTensor facilitates efficient tensor operations and stateful model execution on Apple devices, allowing developers to handle internal state like KV-caches and optimize performance for on-device inference.

Related Skills

Explore More Software Engineering Skills→
tuliopc23tuliopc23

axiom-ios-ml

Convert PyTorch and TensorFlow models to CoreML for on-device iOS inference.

Community
Advanced
pradeepmoulipradeepmouli

axiom-ios-ml

Convert PyTorch models to CoreML and optimize for iOS/macOS deployment.

Community
Advanced
pradeepmoulipradeepmouli

coreml

Convert PyTorch and TensorFlow models to CoreML for on-device inference.

Community
Advanced
tuliopc23tuliopc23

coreml-diag

Diagnose CoreML model loading, performance, and conversion issues on Apple devices.

Community
Advanced