GPU types & models

Compare 90 GPU types tracked across our provider network. Filter by VRAM, brand and pricing to find the right fit.

Choose the right GPU

Quick heuristics for common workloads.

High-VRAM accelerators like H100, H200 and A100 for large language models and deep learning research.

Optimized GPUs like L40S, RTX 4090 and RTX 5090 for efficient model serving and inference workloads.

Cost-effective options like the RTX 30 series and older datacenter GPUs for prototyping and testing.

Curated GPU groups for faster discovery.

Latest generation GPUs across datacenter and prosumer lines.

Top-tier accelerators for demanding training and large-scale inference.

Cost-efficient GPUs with strong value for common workloads.

Showing 2 of 90 models.

Flagship NVIDIA H100 Tensor Core GPU with 80 GB HBM3 for exascale HPC, large-language-model training and low-latency AI inference.

NVIDIA H100 NVL dual-GPU solution offering 2x94 GB HBM3 for ultra-large LLM inference and memory-bound AI workloads.