How do you fine-tune Qwen with LoRA in the cloud cheaply?
Which Qwen3, Qwen3.5 and Qwen3.8 sizes fit LoRA or QLoRA on one GPU, the chat-template traps, and what each size costs per hour on Nodus.
lora
7 posts with the tag “lora”
LoRA vs full fine-tuning: when is LoRA good enough?
LoRA matches full fine-tuning on most post-training jobs. Memory and cost math for 8B and 32B models, and when full fine-tuning is worth the GPUs.
How do you fine-tune Llama on your own data in the cloud?
Pick the right Llama, accept Meta's license, format your data in the Llama 3 chat template, then run a LoRA job on a cloud GPU with a cost cap.
How much does it cost to fine-tune a 70B model?
About $1 per million training tokens in GPU time, so $20 to $45 for a 20M-token run. The FLOP math, five GPU setups priced and what doubles it.
How do you fine-tune Mistral 7B on your own data?
Train a LoRA adapter on the bf16 Mistral 7B on one 48 GB GPU, with memory math, a TrainingJob manifest and the break-even rule for faster GPUs.
LoRA vs QLoRA: which should you use to fine-tune an LLM?
Use LoRA when the 16-bit model fits your GPU and QLoRA when it does not. Memory math, a cost break-even rule and the Nodus config for both.
What is the cheapest way to fine-tune Llama on an H100?
Use the lightest method that fits one H100, checkpoint every few minutes and pay only while the job runs. Memory math, a worked cost and a decision rule.