AWS EC2 Instances›GPU Instance›g6›g6.12xlarge

Compared with Rackspace Spot

AWSRackspace Spot
Machineg6.12xlargegpu.vs2.xlargeplusplus
vCPU4824
Memory192 GiB64 GiB
Local disk4 × 940 GB NVMe SSDNone
On-demand / hr--
Spot / hr--

Compute

vCPUs48
Memory192 GiB
Mem / vCPU4.00 GiB
ProcessorEPYC 7R13 Processor
Clock speed2.6 GHz
Architecturex86_64
GPU4
GPU Wattage27 W
GPU ArchitectureAda Lovelace, Ada Lovelace, Ada Lovelace, Ada Lovelace
Video Memory96 GiB
FPGA0
ffmpeg FPS138
CoreMark / sec1,056,861

Storage

Type4 × 940 GB NVMe SSD
Bandwidth20,000 Mbps
Throughput2500 MB/s
IOPS80,000
Base Bandwidth20,000 Mbps
Base Throughput2500 MB/s
Base IOPS80,000
Devices4
NVMe DriveYes
SSDYes
Swap PartitionNo
Local Read IOPS312,500
Local Write IOPS125,000

Networking

Performance40 Gigabit
Max ENIs8
IPv6Yes
GPUNVIDIA L4
Placement GroupSupported
TrunkingYes
Branch Interface114
IPs / ENI30
Baseline Bandwidth40 Gbps

NUMA Architecture

Uses NUMANo
Node CountN/A
Max DistanceN/A
Cores / NodeN/A
Threads / NodeN/A
Memory / NodeN/A
L3 Cache / NodeN/A
L3 Cache SharedN/A

AWS Metadata

Instance typeg6.12xlarge
Full nameG6 Graphics and Machine Learning GPU 12xlarge Extra Large
FamilyGPU instance
Variantg6
GenerationCurrent
Bare MetalNo
EMR supportYes
DedicatedSupported
Introduced2024-04-04
Family sizes

g6.12xlarge

AWS's g6.12xlarge is a GPU instance with 48 vCPU and 192 GiB. Rackspace Spot runs one GPU class, gpu.vs2.xlargeplusplus: a single NVIDIA A30 with 24 vCPU and 64 GiB, in San Jose only. Against this instance's 4 × NVIDIA L4 that is a downgrade per card, honest for inference and not for the training this instance was bought for.

Server comparison caveats
Weaker GPU

The AWS g6.12xlarge puts 4 Ada Lovelace, Ada Lovelace, Ada Lovelace, Ada Lovelace GPUs (96 GiB VRAM) in one machine. Rackspace Spot has a single GPU class and no multi-GPU server, so there is no shape here that places 4 cards behind one host. Per card the NVIDIA A30 (Ampere, 24 GB VRAM) is a step down from what g6.12xlarge carries, and the aggregate is not reachable at all.

That makes this honest for data-parallel inference and embarrassingly parallel batch work, where each card is independent, and dishonest for anything that shards a model across cards or synchronises every step. The catch is location rather than hardware: US West, San Jose is the only Rackspace Spot region that offers it, so latency to your users and egress to your data are the things to check.

No local disk

The AWS g6.12xlarge comes with 4 × 940 GB NVMe SSD attached to the machine. Rackspace Spot servers 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 attached to your Rackspace Spot server, or object storage, and both are slower to read.

Pricing by region

1 hr

Regions are Rackspace Spot locations.

RegionAWS on-demandAWS Spot1-yr Reserved3-yr ReservedRackspace on-demandRackspace SpotOn-demand price savingsSpot price savings
US West, San Josenot sold heren/an/an/a$7.250$0.151n/an/a

Prices updated 17 Nov 2026.

When to use it

Good for
  • ●Machine learning experimentation and fine-tuning
  • ●Remote graphics workstations and rendering
  • ●CUDA-accelerated batch jobs
  • ●Workloads that fit inside 192 GiB of RAM
  • ●Jobs that want 4 × 940 GB of local NVMe scratch space
  • ●Network-heavy services (AWS rates this size at 40 Gigabit)
Avoid if
  • ●The working set needs more than 192 GiB of RAM
  • ●The work is single-threaded. Most of these 48 vCPU would sit idle.
  • ●Anything the CPU can do fast enough. GPU hours are the most expensive on the price list.
  • ●More than 4.00 GiB of RAM per vCPU is needed, since that ratio is fixed for the whole family
Rackspace Spot sells spare capacity at market prices. You pay what the market decides, not a list price.
  • Rackspace 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

How much does g6.12xlarge cost?

AWS publishes no on-demand price for g6.12xlarge in any of the regions this page covers, because it is not sold there. The specifications and the Rackspace Spot prices below still apply.

Can Rackspace Spot run g6.12xlarge GPU workloads?

Rackspace Spot's entire GPU catalog is gpu.vs2.xlargeplusplus: one NVIDIA A30, 24 vCPU and 64 GiB, available in San Jose only. Against g6.12xlarge's 4 × NVIDIA L4 it is a step down per card: fine for inference, not a substitute for training. The pricing table has one row for that reason.

Does the Rackspace Spot equivalent include local NVMe storage?

No. g6.12xlarge ships 4 × 940 GB of local NVMe SSD, rated 312,500 read IOPS. Rackspace Spot servers are network-backed, so a workload that leans on local disk throughput needs block storage or a re-architecture. Everything else about the match still holds.

What is the difference between g6 and g7?

g7 is the newer generation. It runs on Intel Xeon Scalable (Granite Rapids) against g6's AMD EPYC 7R13 Processor. On the CoreMark figures in this dataset, g7.12xlarge scores 1,511,414 per second against g6.12xlarge's 1,056,861. On-demand in US East (N. Virginia) the newer size is 55% more expensive. Neither generation changes the Rackspace Spot side: both map to the same Rackspace Spot servers.

What is a cheaper alternative to g6.12xlarge?

Rackspace Spot gpu.vs2.xlargeplusplus is the closest shape; the table above shows current prices by region. Workloads have to be containerized to run on it.