Instances›AWS EC2›r7gd›r7gd.metal
Compute
vCPUs64
Memory512 GiB
Mem / vCPU8.00 GiB
ProcessorGraviton3 Processor
Clock speed2.5 GHz
Architecturearm64
Storage
Type2 × 1,900 GB NVMe SSD
Bandwidth20,000 Mbps
Throughput2500 MB/s
IOPS80,000
Networking
Performance30 Gigabit
Max ENIs15
IPv6Yes
GPUNone
Family sizes
r7gd.medium1 vCPU · 8 GiB
r7gd.large2 vCPU · 16 GiB
r7gd.xlarge4 vCPU · 32 GiB
r7gd.2xlarge8 vCPU · 64 GiB
r7gd.4xlarge16 vCPU · 128 GiB
r7gd.8xlarge32 vCPU · 256 GiB
r7gd.12xlarge48 vCPU · 384 GiB
r7gd.16xlarge64 vCPU · 512 GiB
r7gd.metal64 vCPU · 512 GiB
r7gd.metal

The r7gd.metal is a memory-optimized AWS EC2 instance: 64 vCPU and 512 GiB of memory, 8.00 GiB per vCPU. In the name, "r" stands for RAM, "7" is the generation, "gd" marks AWS Graviton (ARM) processors and local NVMe storage and "metal" is the size within the r7gd family. It runs on AWS Graviton3 Processor at 2.5 GHz, and AWS introduced it in March 2024. AWS has since shipped r8gd and r9gd. No single Spot node covers 64 vCPU and 512 GiB, so the equivalent is a fleet: 4 × mh.vs1.2xlarge, 64 vCPU and 512 GiB in total, $4.35/hr on AWS in US East (N. Virginia), from $0.084/hr on Rackspace Spot. Spot delivers compute as managed Kubernetes, so a node pool of that size is the native shape of the answer rather than a workaround — provided the workload scales horizontally.

Match qualityVirtualised, not bare metal

r7gd.metal is a full physical server — no virtualisation layer in the way, direct access to the hardware, and a socket count that licensing can verify.

Rackspace Spot no longer sells bare metal; everything in the catalog is a virtual machine. You get the same cores and memory (4 × mh.vs1.2xlarge, 64 vCPU, 512 GiB), but not the dedicated hardware. If you picked r7gd.metal because you needed the real machine — nested virtualisation, per-socket licensing, low-level profiling — this is not a replacement at any price. If you picked it because it is the biggest r7gd, it is the same compute for a lot less.

Runs as a fleetNo single Spot node has 64 vCPU; the largest comparable one has 16. So this runs as 4 nodes. That works if your workload already spreads across machines, and doesn't if one process needs all the cores together.
x86_64 onlyr7gd.metal is Graviton (arm64) and Rackspace Spot has no arm64 nodes, so you'd be moving to x86. You'll need x86 builds of your images, and per-core speed differs between the chips — worth testing before you decide how many nodes to run.
No local diskr7gd.metal comes with 2 × 1,900 GB NVMe SSD attached to the machine. Spot nodes use network storage only, so that disk doesn't come with it. If you were using it as fast scratch space, you'd move to a persistent volume or object storage, which are slower to read.
Pricing by region
1 hr
RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace SpotYou save
US East, N. Virginia$4.355$4.291$2.737$1.882$0.084
$4.271 savings
US Central, Chicagono AWS region$0.084
US Central, Dallasno AWS region$0.524
Hong Kong$5.292$3.334$2.286$0.084
$5.208 savings
Sydney, Australia$5.011$0.716$3.157$2.165$0.084
$4.927 savings
London, UK$5.110$0.573$3.220$2.208$0.524
$4.586 savings
US West, San Jose$4.899$0.571$3.086$2.116$0.008
$4.891 savings
US Central, Dallas 2no AWS region$0.968
When to use it
Good for
  • ●Large JVM heaps and application servers that hold state
  • ●OLAP and business intelligence query engines
  • ●Real-time analytics over hot datasets
  • ●Workloads that fit inside 512 GiB of RAM
  • ●Jobs that want 2 × 1,900 GB of local NVMe scratch space
  • ●Network-heavy services — AWS rates this size at 30 Gigabit
  • ●Anything that shards cleanly across 4 nodes, which is how it maps onto Rackspace Spot
Avoid if
  • ●The working set needs more than 512 GiB of RAM
  • ●You cannot rebuild x86-only binaries or vendor images for aarch64
  • ●You need dedicated hardware. Rackspace Spot sells virtualised compute only.
  • ●CPU-bound work. You are paying for memory this workload will not use.
  • ●More than 8.00 GiB of RAM per vCPU is needed — that ratio is fixed for the whole family
  • ●The work is single-threaded. Most of these 64 vCPU would sit idle.
Stop overpaying AWS. This compute costs $3,179/mo on AWS vs $61/mo on Rackspace Spot.
  • 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