Local LLM Setup: Intel MacBook Air 2017

MacOS 12 and an Intel chip are essentially blocking me from using Ollama, which is frustrating since I want to stop relying entirely on paid API calls. Since I can't upgrade the OS further, I'm looking for a way to get a local LLM agent running on this hardware.

The main issue is the compatibility gap between current "modern" local runners and older Intel Mac hardware/software versions. I need a lightweight alternative that doesn't have the strict requirements Ollama does.

I've been looking into a few potential workarounds:

1. LM Studio: It usually has better backward compatibility with Intel Macs than Ollama, though RAM is going to be the primary bottleneck here.
2. llama.cpp: This is the gold standard for "running things from scratch." Since it's C++, I can likely compile it directly on my machine, bypassing the MacOS 12 restriction that kills the Ollama installer.
3. GPT4All: Another option that tends to be more lenient with older hardware.

For those who have managed to get a deployment working on 2017-era Airs, how did you handle the memory pressure? I'm guessing only the smallest quantized models (like Phi-3 or TinyLlama) will actually be usable without the system swapping to death.

If anyone has a specific make command or a build flag for llama.cpp that optimizes for these older Intel integrated graphics, that would be a huge help.