sciences44/mlx-lora-finetune

Fine-tune Qwen3.5 for Text-to-SQL on your Mac with MLX LoRA — no GPU required. 4-model comparison, prompt engineering benchmark, and honest limitations.

7 best points · 1 comments · 1 Hacker News post · 10 GitHub stars · View on GitHub

Hacker News discussions

• Show HN: I fine-tuned Qwen 3.5 (0.8B–4B) on a Mac for text-to-SQL – 2B beats 12B (7 points, 1 comments, by sciences44, 2026-03-05)