QLoRA
4-bit quantized fine-tuning method with LoRA adapters
Episodes
-
#5922: Teaching a Model Your Voice: SFT vs DPOThree ways to teach a model your writing voice — and the evidence says one of them quietly makes things worse. -
#5411: Fine-Tuning at 4-Bit vs 16-Bit: What It Really CostsQLoRA cuts fine-tuning VRAM 15x and cost up to 85% — but you pay in training time, quality, and safety alignment. -
#3406: LoRA Isn’t Just for Image GenerationLoRA lets you fine-tune an LLM’s behavior with a 50MB file. Here’s how it works and why it matters. -
#2517: How Unsloth Makes LLM Fine-Tuning 2x FasterUnsloth cuts memory usage by 50-70% and speeds up training 2.2x for models like Llama 3 and Mistral. -
#1907: Why We Still Fine-Tune in 2026Despite million-token context windows, fine-tuning remains essential. Here’s why behavior, not just facts, matters.