GeForce RTX 3060 12GB is generally minimum recommended for AI inference and some training
AMD seems to sell these accelerators, which are like video cards.
UMA buffer size is the size of memory used by APU. It is set on the motherboard, often limited to 2GB. But LLM AI could use 16GB or more.
Event Driven Architecture - video by Martin Fowler
Article comparing cheaper video cards 2023
Context, Software Engineering, Fault Tolerance, Flight
