Instances›AWS EC2›c3›c3.4xlarge
Compute
vCPUs16
Memory30 GiB
Mem / vCPU1.88 GiB
ProcessorXeon E5-2680 v2
Clock speed2.8 GHz
Architecturex86_64
Storage
Type2 × 160 GB SSD
Bandwidth2,000 Mbps
Throughput250 MB/s
IOPS16,000
Networking
PerformanceHigh
Max ENIs8
IPv6Yes
GPUNone
Family sizes
c3.large2 vCPU · 3.75 GiB
c3.xlarge4 vCPU · 7.5 GiB
c3.2xlarge8 vCPU · 15 GiB
c3.4xlarge16 vCPU · 30 GiB
c3.8xlarge32 vCPU · 60 GiB
c3.4xlarge

c3.4xlarge is AWS's compute-optimized EC2 size at 16 vCPU and 30 GiB. In the name, "c" stands for compute, "3" is the generation and "4xlarge" is the size within the c3 family. It runs on Intel Xeon E5-2680 v2 (Ivy Bridge) at 2.8 GHz, and AWS introduced it in November 2013. AWS has since shipped c4, c5, c6i and c7i; c4.4xlarge is the direct replacement at this size, scoring 268,007 CoreMark/s against this instance's 237,989 — roughly 13% more throughput for the same vCPU count. On Rackspace Spot the same shape is ch.vs1.2xlarge — 16 vCPU, 32 GiB, matched on both dimensions, about 95% below the US East (N. Virginia) on-demand rate.

Match qualityNo local disk

c3.4xlarge comes with 2 × 160 GB SSD attached to the machine. Rackspace Spot nodes use network storage only, so that disk does not come with it.

If you were using the local disk as fast scratch space — temporary files, a local cache, an index — you will need a persistent volume or object storage instead, and both are slower to read. If it was just extra space you never depended on, nothing changes.

Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$0.840$0.342$0.584$0.041
$0.799 savings
US Central, Chicagono AWS region$0.011
US Central, Dallasno AWS region$0.111
Hong Kong$0.041
Sydney, Australia$1.058$0.359$0.784$0.041
$1.017 savings
London, UK$0.131
US West, San Jose$0.956$0.247$0.720$0.478$0.002
$0.954 savings
US Central, Dallas 2no AWS region$0.122
US East, N. Virginia 2$0.840$0.342$0.584$0.162
$0.678 savings
When to use it
Good for
  • ●Video encoding and transcoding
  • ●High-traffic web and API serving
  • ●Scientific modelling and simulation
  • ●Workloads that fit inside 30 GiB of RAM
  • ●Jobs that want 2 × 160 GB of local SSD scratch space
Avoid if
  • ●Starting a new deployment. c4.4xlarge is the newer generation at this size.
  • ●The working set needs more than 30 GiB of RAM
  • ●Memory-hungry applications. A memory-optimized family gives more RAM per dollar.
  • ●More than 1.88 GiB of RAM per vCPU is needed — that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 16 vCPU would sit idle.
  • ●GPU or FPGA acceleration is needed
$613/mo on AWS on-demand against $30/mo on Rackspace Spot for the equivalent — market-priced, not list-priced.
  • 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