Instances›AWS EC2›u7i-8tb›u7i-8tb.112xlarge
Compute
vCPUs448
Memory8192 GiB
Mem / vCPU18.29 GiB
ProcessorXeon Scalable
Clock speed2.9 GHz
Architecturex86_64
Storage
TypeEBS only
Bandwidth100,000 Mbps
Throughput12500 MB/s
IOPS560,000
Networking
Performance100 Gigabit
Max ENIs15
IPv6Yes
GPUNone
Family sizes
u7i-8tb.112xlarge448 vCPU · 8192 GiB
u7i-8tb.112xlarge

u7i-8tb.112xlarge is AWS's memory-optimized EC2 size at 448 vCPU and 8192 GiB. It runs on Intel Xeon Scalable (Sapphire Rapids) at 2.9 GHz, and AWS introduced it in December 2024. Spot's largest VM is 16 vCPU and 128 GiB, so matching this instance would take 59 × 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

u7i-8tb.112xlarge is 448 vCPU and 8,192 GiB. The largest comparable Spot node is mh.vs1.2xlarge at 16 vCPU and 128 GiB, so matching it would take 59 of them. That maths works out, but 59 nodes is a redesign rather than a migration — a single block of 8,192 GiB does not survive being split across a network.

If you chose u7i-8tb.112xlarge because the work genuinely needs 448 cores and 8,192 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$83.720$1.239
$82.481 savings
US Central, Chicagono AWS region$1.239
US Central, Dallasno AWS region$7.729
Hong Kong$1.239
Sydney, Australia$1.239
London, UK$98.338$7.729
$90.609 savings
US West, San Jose$0.117
US Central, Dallas 2no AWS region$14.157
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 8192 GiB of RAM
  • ●Parallel work that can occupy 448 vCPU
  • ●Network-heavy services — AWS rates this size at 100 Gigabit
Avoid if
  • ●The working set needs more than 8192 GiB of RAM
  • ●You want a single-machine Spot equivalent. At this size there is not one.
  • ●More than 18.29 GiB of RAM per vCPU is needed — that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 448 vCPU would sit idle.
  • ●Local NVMe or instance-store disk is a hard requirement
  • ●GPU or FPGA acceleration is needed
u7i-8tb.112xlarge is $61,116/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