g4dn.16xlarge is AWS's GPU EC2 size at 64 vCPU and 256 GiB. In the name, "g" is graphics, "4" is the generation, "dn" marks local NVMe storage and enhanced networking and "16xlarge" is the size within the g4dn family. It runs on Intel Xeon Family at 2.5 GHz, and AWS introduced it in September 2019. AWS has since shipped g5, g6 and g7; g5.16xlarge is the direct replacement at this size, scoring 1,246,915 CoreMark/s against this instance's 914,808 — roughly 36% more throughput for the same vCPU count. Rackspace Spot runs one GPU class, gpu.vs2.xlargeplusplus — a single NVIDIA A30 with 24 vCPU and 64 GiB, in San Jose only. Against this instance's 1 × NVIDIA T4 Tensor Core that is a fair swap for inference and media work — the A30 carries more memory and more throughput per card — and it prices $5.22/hr on AWS in US West (N. California), from $0.191/hr on Rackspace Spot.
Match qualityComparable GPU
g4dn.16xlarge pairs 1 Turing GPU (16 GiB VRAM) with 64 vCPU. Spot's GPU node uses the NVIDIA A30 (Ampere, 24 GB VRAM) with 24 vCPU and 64 GiB of memory — newer hardware with more GPU memory, but 24 vCPU against 64. For inference, batch transcoding and single-card fine-tuning the card is the upgrade; anything CPU-bound running alongside it gets less to work with. The catch is location rather than hardware: US West, San Jose is the only Spot region that offers it, so latency to your users and egress to your data are the things to check.
No local diskg4dn.16xlarge comes with 1 × 900 GB NVMe SSD attached to the machine. Spot nodes use network storage only, so that disk doesn't come with it. If you were using it as fast scratch space, you'd move to a persistent volume or object storage, which are slower to read.
