# MLX-LM Apple Silicon: M-Series Mac'te FT + Serve + Distributed MLX

> Source: https://sukruyusufkaya.com/learn/fine-tuning-cookbook/ftc-mlx-lm-apple-silicon-finetune-serve
> Updated: 2026-08-13T19:37:53.754Z
> Category: Fine-Tuning Cookbook (Model-by-Model)
> Module: Part XV — Serving Engineering
**TLDR:** Apple MLX (2023+) — Apple Silicon (M1/M2/M3) için unified memory ML framework. MLX-LM ile Llama / Qwen / Gemma FT + inference. M3 Max 128GB'da 70B inference, M2 Pro 32GB'da 8B FT. RTX 4090 alternatifi olarak Mac kullananlar için cookbook ek section.