⚡️🤖 FLASH - Today, as part of my work on AI, I managed to get Gemma 4 and Qwen 3.X running locally on my PC with llama.cpp
The result: aside from the privacy concerns, I don’t see any point ...
I have recently also played a bit with llama.cpp
Best performance for your hardware is by running a model that uses most of the VRAM. A good match for me has been Qwen 3.5 9B Uncensored. I just tried chatbot things, and it has been pretty good.
Best performance for your hardware is by running a model that uses most of the VRAM. A good match for me has been Qwen 3.5 9B Uncensored. I just tried chatbot things, and it has been pretty good.
1