I use local LLMs all the time. I have a Mac and have used Ollama, LM Studio, oMLX, llama.cpp, and I’m currently looking at Dolphin.
Models I’ve used include Gemma4, Muse Glimmer , Qwen3.5 (and 3.6 - 3.8), plus various others.
I use local LLMs all the time. I have a Mac and have used Ollama, LM Studio, oMLX, llama.cpp, and I’m currently looking at Dolphin.
Models I’ve used include Gemma4, Muse Glimmer , Qwen3.5 (and 3.6 - 3.8), plus various others.