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
- Musk amplifies dev's verdict: Grok Bot easier to use than Codex and Claude — elonmusk · 2026-10-15
- Blob0 launches: a macOS file-manager-style desktop client for S3 and Cloudflare R2 — yihui_indie · 2026-10-15
- The 6-Layer AI Engineer Skill Stack for 2026: Vectors to Multi-Agent Ops — mdancho84 · 2026-10-15
- Building a Mechanical Engineering Agent Workflow in ChatGPT: 30-Node Canvas Shows Promise — burhop · 2026-10-15
- Open-source Harness Engineering course hits 19k stars, shows $9 vs $200 gap between failing and working agent setups — thisguyknowsai · 2026-10-15
- A 6-person team shipped healthcare prior-auth AI agents in 3 months — here's the playbook — alex_verem · 2026-10-15