Heading Logo
Select a price timescale for the search results
Compare
No continents available
No spot or on-demand price data for current filters.
No Matching Products
Provider
Amazon Web Services
CPU
Xeon Scalable (Cascade Lake)
vCPU
96 vCPUs
Architecture
x86_64
Vendor
Intel
Threads/Core
2 threads
ISA Extensions
SSE4.2, AVX2, AVX-512
Memory
192 GB
GPU Count
16 GPUs
Category
Machine Learning Optimized
Availability
Current
Inf1 uses AWS Inferentia accelerators with Intel host CPUs to deliver low-latency, high-throughput inference at low cost.