Kuzco SDK Documentation

Run LLMs, vision models, and image generation locally on iOS devices. Complete privacy. No internet required.

Quick Example

Get up and running with just a few lines of code:

ContentView.swift
import Kuzco
// Initialize once at app startup
KuzcoClient.initialize(apiKey: "kzc_your_api_key_here")
// Create a session and stream responses
let session = try await KuzcoSession(model: .qwen3_4b)
for try await partial in session.streamResponse(to: "Hello!") {
print(partial.text, terminator: "")
}

Core Features

Text Generation

Stream or generate complete responses with multiple LLM options including Qwen, LLaMA, Phi, and Gemma models.

Image Generation

Generate images locally using Stable Diffusion 2.1 with customizable dimensions and inference steps.

Vision AI

Analyze images and answer questions about visual content with Qwen VL and SmolVLM models.

Complete Privacy

All processing happens on-device. No data leaves the user's device, ensuring complete privacy.

Ready to get started?

Follow our installation guide to add Kuzco to your iOS project.

Get Started