Kuzco: Open-source Swift Package for On-Device LLMs on iOS and macOS
By
JC
Crisp on the outside, thoughtful on the inside. A keeper.
Summary
Kuzco is an open-source Swift package designed to integrate large language models (LLMs) into iOS, macOS, and Mac Catalyst apps. Built on `llama.cpp`, it provides customizable prompts, flexible tuning, and async/await-friendly APIs for on-device AI.
Key quotes
· 2 pulledKuzco is a Swift package for integrating large language models (LLMs) directly into iOS, macOS, and Mac Catalyst apps.
Built on `llama.cpp`, it offers customizable prompts, flexible tuning, and async/await-friendly APIs for on-device AI.
You might also wanna read
A practical guide to running local LLMs on macOS for experimentation and privacy
A developer shares their skeptical yet practical guide to downloading and running large language models locally on macOS. The article covers
blog.6nok.org·8mo ago
Introduction to uzu: High-Performance Inference Engine for AI Models on Apple Silicon
A high-performance inference engine for AI models called uzu is introduced, designed for Apple Silicon. The engine supports its own model fo
github.com·10mo ago
Mozilla.ai's llamafile: Run LLMs with a single executable file
llamafile is a Mozilla.ai project that simplifies running large language models (LLMs) by combining llama.cpp with Cosmopolitan Libc into a
github.com·5mo ago
LlamaFactory: Open-Source Framework for Efficient Fine-Tuning of 100+ LLMs and VLMs
LlamaFactory is an open-source framework for unified efficient fine-tuning of 100+ large language models (LLMs) and vision-language models (
github.com·8mo ago