QLoRA fine-tune on a single 48 GB GPU; memory cut from >780 GB to <48 GB without quality loss
65B on 48 GBobserved
| Value kind | observed — Reported measurements, counts, and specifications keep the precision and scope stated by their source; an exact specification is not treated as a range. |
|---|---|
| As of | 2023 |
| Source | QLoRA (Dettmers et al., arXiv 2305.14314) · Abstract: fine-tunes a 65-billion-parameter model on a single 48 GB GPU |
| Review | checking…review by 2026-08-29 · standard cadence |
| Recorded changes | last 2026-07-07 |
| Claim id | qlora-fine-tune-on-a-single-48-gb-gpu-memory |
Where the guide uses it
← Full numbers register — every date-stamped figure in the guide, with revision history.