Quite slow, but fully local and 0 costs.
Login to reply
Replies (9)
This is the way
I've got to get stacking. Slow and steady is what I want anyway. Claude's fast but unpredictable, and it's wearing thin.
💯
0 costs? You’re not upgraded any hardware?
This runs on my daily use laptop
What are the laptops specs? And the model?
Switch to llama.cpp and get much better performance. But ollama makes things easier, but at a cost
My framework laptop 16 AMD Ryzen HX370 with a integrated GPU Radeon 890M. Memory is one DDR5-5600 - 48GB item.
View quoted note →
Very nice.