RAG, Fine-Tuning & ContextTim Dettmers et al.
QLoRA
QLoRA
Why it matters
Fine-tunes a 65B model on a single 48 GB GPU using 4-bit NF4, double quantization and paged optimizers
Source — Primary sources first; secondary reports are labelled “Press”
Paperarxiv.orghttps://arxiv.org/abs/2305.14314Added in Week 35, 2026 · See that week