MLX LM: Inferencia y Ajuste Fino de LLMs en Apple Silicon

Fri, 01 May 2026 00:00:00 +0000

The promise of running LLMs locally on a MacBook has been seductive but incomplete. Ollama and llama.cpp made it possible, but performance left room for improvement — models ran, but they did not fully leverage Apple Silicon’s architecture. The gap between what a MacBook could theoretically do and what inference engines delivered was visible in every benchmark.

MLX LM closes this gap. Built on Apple’s own MLX framework, it runs LLM inference and fine-tuning at speeds that previously required dedicated GPU hardware. The key is MLX’s unified memory architecture — no data copying between CPU and GPU, no PCI-e bottlenecks, just direct access to the full memory bandwidth of Apple Silicon. For a MacBook Pro with an M4 Max, MLX LM delivers inference performance that rivals mid-range NVIDIA GPUs.

Unsloth: Ajuste Fino de LLMs 2x mas Rapido con Memoria Reducida

Fri, 01 May 2026 00:00:00 +0000

Fine-tuning large language models on consumer hardware has been a game of memory optimization Tetris. Every byte of GPU memory is precious — model weights, optimizer states, gradients, and activations all compete for space. Parameter-efficient techniques like LoRA and QLoRA reduced the memory barrier significantly, but running these techniques efficiently required a level of CUDA optimization expertise that most developers do not have.

Unsloth exists to solve this. It is an open-source library that provides drop-in optimizations for fine-tuning popular LLMs using LoRA and QLoRA. The numbers speak for themselves: 2x faster training, 50% less memory usage, and identical model output quality. The optimizations are transparent — you use the same Hugging Face APIs you already know, and Unsloth handles the low-level kernel optimization automatically.

Fine-Tuning on SoloSoft

MLX LM: Inferencia y Ajuste Fino de LLMs en Apple Silicon

Unsloth: Ajuste Fino de LLMs 2x mas Rapido con Memoria Reducida