Part 3 of a 4-part series. QLoRA explained — quantize the frozen base to 4-bit, then LoRA on top. The BitsAndBytesConfig that matters, the memory-footprint moment, and why it's about fit, not speed.
QLoRA: Fine-Tuning a 7B Model on a 16GB GPU (It Shrank to 5.4GB in Front of Me)
