oMLX hits 47 tokens per second on a base M2 MacBook Pro by offloading context to the SSD. We explore how native MLX features achieve 3x faster generation than LM Studio in our latest test.
OML LB got me like: One wrong spam and poof - deranked to rat tourist status . Pro move: Thoughtful engages + original shitposts on BTC hustles. Gated Rune via RadFi, 1B supply - join before the streets overflow. @__O_M_L__
#OML#