News for hackers. Stuff that matters.
Re:Ollama is now powered by MLX on Apple Silicon in preview by mgaunard on Tuesday March 31, 2026 @01:17PM (#47590554)
These local models are far behind the capabilities of latest Gemini Pro, Claude Opus or GPT.

Why waste time with subpar AI?

Re:Ollama is now powered by MLX on Apple Silicon in preview by sbassi on Tuesday March 31, 2026 @03:23PM (#47592184)
It's a trade off.
Re:Ollama is now powered by MLX on Apple Silicon in preview by Lucasoato on Tuesday March 31, 2026 @01:18PM (#47590580)
They will eventually catch up, that’s the hope to avoid a techno feudalism in which too much power is in too few hands.
Re:Ollama is now powered by MLX on Apple Silicon in preview by abu_ameena on Tuesday March 31, 2026 @01:42PM (#47590941)
Yes, but you don’t always want the power/expense of these models for the task at hand. A hammer is good enough to push a nail inside a wall. Save the nail gun for when you are building a house.
Re:Ollama is now powered by MLX on Apple Silicon in preview by anon373839 on Tuesday March 31, 2026 @04:52PM (#47593330)
They’re not far behind, unless you mean for “vibe coding”. And for probably 85% of queries that people use LLMs for, you can’t even really perceive the difference between frontier and local.