Apple
Mac Local LLMs Hit 50% Faster — AI Wrote the Performance Code
Developer used Claude to rewrite Splash inference engine for M5 Max: 50% faster concurrent, ~25% single request. AI now writes performance code.
Back to home
M5 Max
3 articles tagged with this topic
Apple
M5 Max Mac Local AI 20% Faster—Hidden Cost: Per-Gen Kernel Retuning Required
Developer retunes inference kernels for 40-core M5 Max, boosting local LLM generation 20%. Each Apple Silicon generation needs manual AI re-optimizati
AMD
Developer Squeezes AMD GPU Into MacBook Pro, Cracks Apple's Last Hardware Wall
AMD Radeon runs Qwen3 LLMs locally on M5 Max MacBook Pro. Developer ports Linux driver to macOS via Thunderbolt 5 — third hardware path.