Use Cases
GPU & LLM Compute Use Cases
Different AI workloads have different hardware requirements. Browse by use case to find the GPUs and cloud providers best matched to your workload — with live pricing and side-by-side comparisons.
LLM Inference
Serve language models at scale. Compare GPUs and providers optimised for low-latency, high-throughput token generation.
ExploreModel Training
Pre-train or train from scratch. Find the highest-memory, highest-bandwidth GPUs and multi-node clusters for large-scale runs.
ExploreFine-Tuning
Adapt a foundation model to your domain. Identify cost-effective GPUs and providers suited to LoRA, QLoRA, and full fine-tune jobs.
ExploreBy GPU model
Workload fit, VRAM guidance, and live pricing for the most widely available GPU models.
All GPU use cases