Looking to optimize your costs? Here are 3 tips for running open models in the cloud 👇
- Looking to optimize your costs? Here are 3 tips for running open models in the cloud 👇
#1: Enable Scale-to-Zero Enable scale-to-zero in Model Garden to automatically power down your GPU instances when there are no active incoming requests. Model Garden docs ↓#2: Leverage Spot VMs Many developer and agent testing workflows are resilient and don’t require 100% continuous uptime. Choose Spot as your VM provisioning model to tap into spare Google Cloud compute capacity at deep discounts.#3: Right-Size Your Hardware + Limit Auto-Scaling Keep your monthly bill predictable by updating your settings to apply strict hardware limits, such as: - capping your accelerator count at a single GPU - locking your replica count to 1-1 - opting for no capacity reservations
