Show HN: All local LLM(s) on all Apple Devices

Category: devtools

Tags: apple-silicon, local-llm, performance-simulator, mlx, llama-cpp

Score: 6.0/10 (Innovation: 6, Technical: 5, Documentation: 7, Utility: 7)

Simulkit is a simulator that estimates running speed (tokens per second) for local LLMs on every Apple Silicon Mac, using chip memory bandwidth, GPU compute, and memory fit constraints. It provides detailed guidance on model quantization, MoE behavior, and macOS memory limits, helping users decide which Mac to buy or which model to run.

Target audience: Apple users, AI enthusiasts, machine learning engineers, and developers running local LLMs

Repository: https://simulkit.com/en/mac-local-llm

View on Hacker News