Instances›AWS EC2›g6›g6.24xlarge
Compute
vCPUs96
Memory384 GiB
Mem / vCPU4.00 GiB
ProcessorEPYC 7R13 Processor
Clock speed2.6 GHz
Architecturex86_64
Storage
Type4 × 940 GB NVMe SSD
Bandwidth30,000 Mbps
Throughput3750 MB/s
IOPS120,000
Networking
Performance50 Gigabit
Max ENIs15
IPv6Yes
GPUNVIDIA L4
Family sizes
g6.xlarge4 vCPU · 16 GiB
g6.2xlarge8 vCPU · 32 GiB
g6.4xlarge16 vCPU · 64 GiB
g6.8xlarge32 vCPU · 128 GiB
g6.12xlarge48 vCPU · 192 GiB
g6.16xlarge64 vCPU · 256 GiB
g6.24xlarge96 vCPU · 384 GiB
g6.48xlarge192 vCPU · 768 GiB
g6.24xlarge

The g6.24xlarge pairs 96 vCPU with 384 GiB of RAM, the 4.00 GiB-per-vCPU ratio that marks a GPU instance. In the name, "g" is graphics, "6" is the generation and "24xlarge" is the size within the g6 family. It runs on AMD EPYC 7R13 Processor at 2.6 GHz, and AWS introduced it in April 2024. AWS has since shipped g7; g7.24xlarge is the direct replacement at this size, scoring 2,780,795 CoreMark/s against this instance's 1,884,200 — roughly 48% more throughput for the same vCPU count. 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.

Match qualityWeaker GPU

g6.24xlarge puts 4 Ada Lovelace, Ada Lovelace, Ada Lovelace, Ada Lovelace GPUs (96 GiB VRAM) in one machine. Spot has a single GPU class and no multi-GPU node, 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 g6.24xlarge 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 Spot region that offers it, so latency to your users and egress to your data are the things to check.

No local diskg6.24xlarge comes with 4 × 940 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 West, San Jose$0.191
When to use it
Good for
  • ●Model inference and embedding generation
  • ●Video transcoding and image processing
  • ●Machine learning experimentation and fine-tuning
  • ●Workloads that fit inside 384 GiB of RAM
  • ●Jobs that want 4 × 940 GB of local NVMe scratch space
  • ●Network-heavy services — AWS rates this size at 50 Gigabit
Avoid if
  • ●The working set needs more than 384 GiB of RAM
  • ●The work is single-threaded. Most of these 96 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 — 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.
  • 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