After playing around with ollama a couple of weeks ago, I was curious how much faster the models run on newer Macbooks. At the end of this, I was hoping to find an LLM that can run reasonably well on my Intel Macbook Pro, but also see how that compares to other machines I had around at the time. I picked Llama3:8B, Phi-3:4B and Gemma:9B models and ran them on 4 devices: 2023 Macbook Pro 14” with M3 Pro 2021 Macbook Pro 14” with M1 Pro 2019 MBP 16” with 2.6 GHz 6-Core Intel Core i7 Windows deskt...