PocketPal is good, has built in huggingface search and download, only text chat (no multimodal yet), support last models from llama-cpp, as:

• gemma3 (just released)
• falcon3
• phi-4-mini
• granite3.2

My gear is an old:

I7-4790 16GB RAM

How many tokens by second?

It’s not out of my scope, I’m just learning what can I do locally with my current machine.

Today I read about RAG, maybe I’m gonna try an easy local setup to chat with a PDF.