architecture
Turing / Volta / Pascal / Maxwell
platforms
T4, V100, P100, P40, M60
memory
Up to 32GB HBM2 / GDDR5
tensor cores
Available on select models
precision
FP32, FP16, INT8
interconnect
PCIe / NVLink (select models)
virtualization
VDI & vGPU Support
deployment
Budget Datacenters & Enterprise Labs
best for
Budget AI Infrastructure, Virtualization, Development Environments, Legacy Compute Workloads
features
Affordable GPU acceleration, Reliable inference performance, Efficient virtualization support, Legacy application compatibility, Flexible enterprise deployment
Cost-effective GPU infrastructure for inference, development, testing, and budget-focused deployments.
Popular Models:
T4
V100
P100
P40
M60
Best For:
Budget AI infrastructure, virtualization, development environments, and legacy compute workloads.