← All instances

inf2.24xlarge

⚡ 6x GPU • 192.0 GB

Part of the INF2 Accelerated Computing family — Hardware accelerators (GPUs, FPGAs) for specialized compute.

Name:infAWS Inferentia Acceleratorsinf = AWS Inferentia AcceleratorsPurpose-built AWS Inferentia silicon designed for ultra-low latency, high-throughput machine learning inference.22nd Generation2 = 2nd GenerationAWS 2nd generation hardware platform with updated CPU/system architecture.24xlarge24 Extra Large24xlarge = 24 Extra Large96 vCPUs • 384.0 GiB RAM • EBS only • 50 Gigabit Network • 6x GPU (192.0 GB VRAM)
Price (Linux)
$6.4906/ hr
~$4,738.16/mo
Compute
96vCPUs
48 cores • x86_64
Memory
384.0GiB
4.0 GiB / vCPU
Value
$0.0676/ vCPU-hr
$0.0169/GiB-hr
Network
50Gbps
Baseline: 50 Gbps
Storage & EBS
3,750MB/s
Max: 120,000 IOPS

Technical Specifications & Limits

Hardware specs, container thresholds, and system limits

Compute & Processor

ProcessorAMD EPYC 7R13 Processor
Architecturex86_64 (x86_64)
vCPUs / Threads96 vCPUs
Physical Cores48
Clock Speed2.95 GHz
Intel AVX / AVX2No
Intel Turbo BoostNo
Bare MetalNo (Virtualized)

Performance & Benchmarks

CoreMark Score1,914,734
CoreMark / vCPU19,945.2 / core
FFmpeg Transcoding249 FPS
CoreMark per Dollar295,000 score / $
Cost per vCPU-hr$0.0676
Cost per GiB-hr$0.0169

Containers & Kubernetes

EKS Max Pods737 pods
Max ECS Tasks120 tasks
Max ENIs15
IPv4/v6 per ENI50
Total Addressable IPs750 total IPs
CNI Prefix DelegationSupported (High Density)

Networking & Bandwidth

Network Performance50 Gigabit
Baseline Bandwidth50 Gbps
Burst / Peak Bandwidth50 Gbps
Enhanced NetworkingYes
EFA SupportNo
IPv6 SupportNative Dual-Stack Supported

Storage & EBS Optimization

Storage ConfigurationEBS only
Local NVMe DiskNone (EBS only)
EBS Baseline Throughput3750 MB/s
EBS Max Throughput3750 MB/s
EBS Baseline IOPS120,000
EBS Max / Burst IOPS120,000
Dedicated EBS Throughput30 Gbps

GPU & Hardware Acceleration

GPU ModelNVIDIA Accelerator
Accelerator Count6x GPU(s)
Total GPU Memory192.0 GB
Memory ArchitectureGDDR / HBM
CUDA Compute Capability—
Acceleration RuntimesCUDA, TensorRT, cuDNN, PyTorch, PyJAX

Platform & Architecture Details

Hypervisor / SystemAWS Nitro System (PCIe Offload)
Nitro EnclavesSupported (Isolated security enclaves)
Normalization Factor8.560582329
Generation StatusCurrent Generation (Recommended)
Date Introduced2023-04-13

Regional Pricing Matrix

Live on-demand rates across all global AWS cloud regions
Lowest Price Region
$6.4906/ hr
US East (N. Virginia) (us-east-1)
Highest Price Region
$11.0341/ hr
South America (Sao Paulo) (sa-east-1)
Global Fleet Average
$8.4628/ hr
Across all active regions
Regional Coverage
13regions
Available worldwide
Linux — Available in all 13 regions
Region NameRegion CodeOn-Demand Price
Asia Pacific (Mumbai)
ap-south-1$8.4378
Asia Pacific (Singapore)
ap-southeast-1$9.0869
Asia Pacific (Sydney)
ap-southeast-2$8.4378
Asia Pacific (Tokyo)
ap-northeast-1$9.7360
EU (Frankfurt)
eu-central-1$9.7360
EU (Ireland)
eu-west-1$8.1133
EU (London)
eu-west-2$9.7360
EU (Paris)
eu-west-3$9.0869
EU (Stockholm)
eu-north-1$7.1397
South America (Sao Paulo)Highest
sa-east-1$11.0341
US East (N. Virginia)Lowest
us-east-1$6.4906
US East (Ohio)Lowest
us-east-2$6.4906
US West (Oregon)Lowest
us-west-2$6.4906