Instances›AWS EC2›u7in-32tb›u7in-32tb.224xlarge
Compute
vCPUs896
Memory32768 GiB
Mem / vCPU36.57 GiB
ProcessorXeon Scalable
Clock speed2.9 GHz
Architecturex86_64
Storage
TypeEBS only
Bandwidth100,000 Mbps
Throughput12500 MB/s
IOPS560,000
Networking
Performance200 Gigabit
Max ENIs16
IPv6Yes
GPUNone
Family sizes
u7in-32tb.224xlarge896 vCPU · 32768 GiB
u7in-32tb.224xlarge

The u7in-32tb.224xlarge pairs 896 vCPU with 32768 GiB of RAM, the 36.57 GiB-per-vCPU ratio that marks a memory-optimized instance. It runs on Intel Xeon Scalable (Sapphire Rapids) at 2.9 GHz, and AWS introduced it in May 2024. Spot's largest VM is 16 vCPU and 128 GiB, so matching this instance would take 233 × mh.vs1.2xlarge — arithmetically true and operationally absurd. The Spot column below prices that whole fleet, so read it as a scale reference rather than a drop-in replacement: at this size the useful question is what a shard of the workload costs, which is $0.021/hr per node.

Match qualityNo single-node equivalent

u7in-32tb.224xlarge is 896 vCPU and 32,768 GiB. The largest comparable Spot node is mh.vs1.2xlarge at 16 vCPU and 128 GiB, so matching it would take 233 of them. That maths works out, but 233 nodes is a redesign rather than a migration — a single block of 32,768 GiB does not survive being split across a network.

If you chose u7in-32tb.224xlarge because the work genuinely needs 896 cores and 32,768 GiB together — an in-memory database, a large analytics engine, a single big solver — Rackspace Spot has no equivalent. What does fit is everything around it: the application servers, batch workers and CI that talk to that machine, which is usually the larger share of the bill.

Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$360.987$222.456$115.985$4.893
$356.094 savings
US Central, Chicagono AWS region$4.893
US Central, Dallasno AWS region$30.523
Hong Kong$4.893
Sydney, Australia$4.893
London, UK$30.523
US West, San Jose$0.466
US Central, Dallas 2no AWS region$56.386
When to use it
Good for
  • ●In-memory caches such as Redis and Memcached
  • ●Large JVM heaps and application servers that hold state
  • ●OLAP and business intelligence query engines
  • ●Workloads that fit inside 32768 GiB of RAM
  • ●Parallel work that can occupy 896 vCPU
  • ●Network-heavy services — AWS rates this size at 200 Gigabit
Avoid if
  • ●The working set needs more than 32768 GiB of RAM
  • ●You want a single-machine Spot equivalent. At this size there is not one.
  • ●GPU or FPGA acceleration is needed
  • ●CPU-bound work. You are paying for memory this workload will not use.
  • ●More than 36.57 GiB of RAM per vCPU is needed — that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 896 vCPU would sit idle.
u7in-32tb.224xlarge is $263,521/mo on AWS on-demand. A mh.vs1.2xlarge node on Rackspace Spot is $15/mo — at this size the per-node price is the honest comparison.
  • Spot sells spare capacity at market prices. It is the cheapest compute on the internet.
  • Prices are set by supply and demand. You pay what the market decides.
  • Compute is delivered as fully managed Kubernetes. All infrastructure is taken care of.
  • Egress costs $0.01/GB after the free allowance. AWS charges $0.09/GB.
Build your Cloudspace
Frequently asked questions