¿Qué GPU debo alquilar?

Lista de configuración

• Start from a ComfyUI or Automatic1111 template to skip driver and dependency setup.
• Keep checkpoints, LoRAs and outputs on a persistent volume; model files are several GB each.
• Batch generations when you can — interactive, one-at-a-time use leaves the GPU idle most of the hour.
• Check the license of the model you use (Flux dev, for example, is non-commercial).

Cómo se calcula

The wizard starts from memory, because a GPU that can't hold the job is useless at any price. For running a model we size the weights at the precision your priority implies — 4-bit for cheapest, 8-bit for balanced, 16-bit for fastest — plus KV cache for an 8K context. Fine-tuning uses QLoRA (or LoRA when you pick fastest), training uses full mixed-precision state, and image models use typical VRAM needs for each model family.

Among the GPUs that fit and have a live price, cheapest ranks by hourly rate, fastest by memory bandwidth (which sets generation speed), and balanced by price per unit of bandwidth — the most speed per dollar. If no single card fits, it shows the smallest multi-GPU shapes instead. Every result links to the GPU's page with all providers, because the cheapest provider isn't always the most reliable one.