Show HN: LoRA over GGUF – Train Qwen3.8-Flash-Next in 40G VRAM

By woctordho · 2026-10-10 · 1 points · 0 comments

https://github.com/woct0rdho/transformers5-qwen3.5-recipe

Open weight AI is like open source software. Users not only run the weights, but also modify the weights. It matters to develop training framework for local hardware. The method to train large AI models on local hardware is generally called QLoRA (Low Rank Adaptation over Quanti…

Open the full discussion on BetterNews