maxloh 3 days ago

Note that Microsoft do have their own LLM team, and their own model called Phi-4.

https://huggingface.co/microsoft/phi-4

1
VladVladikoff 3 days ago

Recently I was looking for a small LLM that could perform reasonably well while answering questions with low latency, for near realtime conversations running on a single RTX 3090. I settled on Microsoft’s Phi-4 model so far. However I’m not sure yet if my choice is good and open to more suggestions!

mywittyname 3 days ago

I've been using claude running via Ollama (incept5/llama3.1-claude) and I've been happy with the results. The only annoyance I have is that it won't search the internet for information because that capability is disabled via flag.

danielbln 3 days ago

That's.. that's not the Claude people talk about when they say Claude. Just to be sure.