Tag: mlx

All the articles with the tag "mlx".

• Ollama vs llama.cpp vs MLX on a Mac Studio, measured

  20 Sep, 2026

  Qwen3.5 9B through Ollama (GGUF and MLX), llama-bench, mlx-lm and rapid-mlx on an M3 Ultra. Measured tokens per second, memory, and what MTP changes.

  • local-llm
  • ollama
  • llama-cpp