INF2 Accelerated Computing

⚡ GPU Accelerated

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.

Alternatives to inf2

OptionPrice vs inf2Why look at it
g4dnCompare →
-31%-$0.232/hr
xlarge, Linux on-demand, us-east-1		Intel (x86_64), newer generation, same vCPU and RAM
g5Compare →
+33%+$0.248/hr
xlarge, Linux on-demand, us-east-1		Newer generation, same vCPU and RAM
g6Compare →
+6%+$0.0466/hr
xlarge, Linux on-demand, us-east-1		Newer generation, same vCPU and RAM

Common use cases

  • Machine learning training/inference
  • High-performance computing
  • Graphics rendering

Head-to-Head Architecture Comparisons

View all comparisons →
Accelerated & AIg4dn vs g5 vs g6 vs inf2

AWS AI Inference Acceleration: G4dn vs G5 vs G6 vs Inf2

NVIDIA T4 vs A10G vs L4 vs AWS Inferentia2 for LLM and ML model serving

Compare specifications →

Instance types (4)

InstancevCPUMemoryGPU CountGPU MemoryMemory TypeArchitectureFrom (Linux, $/hr)
inf2.xlarge416 GB1x32.0 GBStandardx86_64$0.7582
inf2.8xlarge32128 GB1x32.0 GBStandardx86_64$1.9679
inf2.24xlarge96384 GB6x192.0 GBStandardx86_64$6.4906
inf2.48xlarge192768 GB12x384.0 GBStandardx86_64$12.9813