Inkling 2 Mini Runs Smoothly on 24GB M5 Pro, MLX Beats llama.cpp

User muradylan's benchmarks show Inkling 2 Mini runs about twice as fast with MLX versus llama.cpp on an M5 Pro, and runs smoothly on 24GB RAM despite the stated 32GB requirement.

2026-11-22 ~ 2026-11-22 · 2 related posts