I’m running Ollama on 2 eGPUs over Thunderbolt. Works well for me. You’re still dealing with an NVDIA device, of course. The connection type is not going to change that hassle.
Though I have to ask: why two eGPUs? Is the LLM software smart enough to be able to use any combination of GPUs you point it at?
llama.cpp probably is too, but I haven't tried it with a bigger model yet.