GPU models & rental pricing
Technical specifications, memory architectures, and cross-network price comparisons for AI and rendering workloads.
NVIDIA H100 (80GB HBM3)
The NVIDIA H100 Hopper GPU is the enterprise benchmark accelerator for modern generative AI. With fourth-generation Tensor Cores, a dedicated Transformer Engine, and 3.35 TB/s memory bandwidth, it delivers up to 4x faster training and 30x faster inference compared to the previous generation A100.
NVIDIA A100 (80GB SXM4)
The NVIDIA A100 80GB Ampere GPU remains the foundational workhorse for AI practitioners. Its 80 GB of high-bandwidth HBM2e memory easily accommodates large context windows and multi-gigabyte model weights without memory bottlenecks.
NVIDIA GeForce RTX 4090 (24GB)
The NVIDIA GeForce RTX 4090 is the flagship consumer accelerator based on the Ada Lovelace architecture. It delivers astounding compute-per-dollar, featuring fourth-generation Tensor Cores and third-generation RT cores with 24 GB of ultra-fast GDDR6X VRAM.