LLM Local Client vs MLX Benchmarks

Looking to Run a personal LLM on Your Mobile Device? Instead of installing large models on your phone, consider an alternative solution. This app connects your mobile device to locally hosted large language models (LLMs) on your computer. Using a fast and secure local network, it provides seamless interaction with advanced AI capabilities. Use this app as a bridge to powerful LLMs and unleash your productivity like never before. Key Features: • Lightweight and Easy Setup: Configure and start using the app in just a few steps. • Local Network Security: Your data stays within your trusted environment, ensuring privacy. • Mobile Convenience: Access the power of your local LLM server anytime. • API Compatibility: Designed to work seamlessly with common LLM APIs for maximum flexibility. Perfect for AI enthusiasts and professionals, this app provides a portable, secure solution for leveraging large language models on the go.

MLX Benchmark helps you understand how large language models perform on your hardware. Select a model and quantization, set context length and iterations, and run repeatable benchmarks that capture load time, tokenization time, time to first token, throughput, memory usage, and jitter. View detailed metrics grids, visualize comparisons in charts, and manage downloaded model repos directly in the app. Built for developers and AI enthusiasts who want clear, on-device performance insights without leaving their device. Features: - Model selection with quantization details - Configurable prompt, context length, and iterations - Metrics for load, tokenization, first-token latency, throughput, jitter, and memory - Charts to compare runs and devices - Downloaded model management (list, delete, refresh) - Optional Supabase upload for aggregating benchmark results