Fine-tuned Qwen3.8-27B on custom data using a single 48GB GPU

danielhanchen · x · 2026-08-26

Hands-on Case: The author successfully fine-tuned the Qwen3.8-27B model using proprietary data.
Training Details: Built a custom Q&A dataset in JSONL format from scratch and used Unsloth QLoRA to train the 27B model on a single 48GB GPU.
Results: The base model had no knowledge of the author, while the fine-tuned model answered instantly and accurately in the author's own tone.
Full Pipeline: The video covers dataset creation, training, inference, and a before-and-after comparison.

More from coding & agent