Apple Silicon

concepts · 2 notes linked

Related: Apple · Ollama · Local LLM Inference · Mlx Framework · Model Inference Optimization · Pytorch · GPU Acceleration · Deep Learning

Notes

• Ollama Just Got 93% Faster on Mac. Here's How to Enable It. — Ollama MLX backend delivers 93% decode speedup on Apple Silicon Macs
• Running PyTorch on the M1 GPU — Benchmark of PyTorch M1 GPU support via MPS backend for deep learning training