inf2.24xlarge by Amazon Web Services

inf2.24xlarge is a AWS Inferentia Gen2 24xlarge server offered by Amazon Web Services with 96 vCPUs, 384 GiB of memory and 0 GB of storage. The pricing starts at 0.6491 USD per hour.
96 vCPU
384 GiB Memory
Spare SCore
143,448
(All-cores)
2,991
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
inf2.24xlarge
Description
AWS Inferentia Gen2 24xlarge
Family
inf2
Hw Virt
Status
active
Observed At
2026-10-26T00:02:14.386075

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.680733 USD/h 6.4906 USD/h
Northern Virgina (US) / us-east-1
1.321175 USD/h 6.4906 USD/h
Oregon (US) / us-west-2
1.431625 USD/h 6.4906 USD/h
Stockholm (SE) / eu-north-1
0.996 USD/h 7.1397 USD/h
Dublin (IE) / eu-west-1
2.004167 USD/h 8.1133 USD/h
Mumbai (IN) / ap-south-1
2.49125 USD/h 8.4378 USD/h
Sydney (AU) / ap-southeast-2
5.476 USD/h 8.4378 USD/h
Paris (FR) / eu-west-3
1.6094 USD/h 9.0869 USD/h
Singapore (SG) / ap-southeast-1
5.32655 USD/h 9.0869 USD/h
London (GB) / eu-west-2
1.0736 USD/h 9.736 USD/h
Frankfurt (DE) / eu-central-1
5.73505 USD/h 9.736 USD/h
Tokyo (JP) / ap-northeast-1
9.736 USD/h 9.736 USD/h
Sao Paulo (BR) / sa-east-1
1.1034 USD/h 11.0341 USD/h

Processor

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
3.6 GHz
CPU Architecture
x86_64
CPU Manufacturer
AMD
CPU Family
EPYC
CPU Model
7R13
CPU L1D Cache
32 KiB
CPU L1D Cache Total
2 MiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
2 MiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
24 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
192 MiB
CPU Flags
fpu, vme, de, pse, tsc, msr, pae, mce, cx8, apic, sep, mtrr, pge, mca, cmov, pat, pse36, clflush, mmx, fxsr, sse, sse2, ht, syscall, nx, mmxext, fxsr_opt, pdpe1gb, rdtscp, lm, constant_tsc, rep_good, nopl, nonstop_tsc, cpuid, extd_apicid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, cmp_legacy, cr8_legacy, abm, sse4a, misalignsse, 3dnowprefetch, topoext, perfctr_core, ssbd, ibrs, ibpb, stibp, vmmcall, fsgsbase, bmi1, avx2, smep, bmi2, invpcid, rdseed, adx, smap, clflushopt, clwb, sha_ni, xsaveopt, xsavec, xgetbv1, clzero, xsaveerptr, rdpru, wbnoinvd, arat, npt, nrip_save, vaes, vpclmulqdq, rdpid
Ecpus
48
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
384 GiB
Memory Amount Actual
384 GiB
Memory Generation
DDR4
Memory Speed
3200 Mhz
ACCELERATORS
Accelerator Count
0
Accelerator Memory Min
0 MiB
Accelerator Memory Total
0 MiB
Accelerators
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      50 Gbps
      Network Speed Max
      50 Gbps
      Network Storage Speed Baseline
      30 Gbps
      Network Storage Speed Max
      30 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      A high-density, multi-core x86_64 platform featuring balanced memory allocation and 50 Gbps networking for parallelized enterprise workloads.

      General PurposeCompute Optimized

      Amazon Web Services inf2.24xlarge is an x86_64 server running on the Nitro hypervisor, featuring a dedicated 96-vCPU AMD EPYC 7R13 processor at 3.6 GHz and 384.0 GB of DDR4 memory. It lacks local storage and dedicated GPUs, but provides a 50 Gbps baseline network bandwidth. Performance benchmarks show top-tier multi-core CPU execution and memory subsystem efficiency, alongside strong cryptographic capabilities. Single-core processing and large-block memory bandwidth remain average. With a balanced 1:4 vCPU-to-RAM ratio, this instance is optimized for multi-threaded workloads such as database operations, software compilation, and Redis-based caching.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      2.9Score
      Precomputed compound score for Cache Intensive workloads. A weighted average (geometric mean) of benchmark scores compared to their medians: score = ∏ (x_i / m_i)^(w_i / Σw). The score of 1.0 represents a synthetic baseline server with the median performance of each component benchmark; 0.5 means roughly half the performance; and 2.0 means twice the performance of that reference profile. Component weights: 50% Redis RPS (pipeline=1, SET), 20% Redis RPS (pipeline=16, SET), 10% PassMark Memory Mark (composite), 10% Memory bandwidth (read, 16 MB ~ L3), 10% PassMark single-thread CPU. Rationale for component selection: In-memory key-value store workload, mixing direct Redis performance metrics with memory speed and latency benchmarks, and single-core CPU performance profiles.
      Component Score Weight Impact
      Raw Reference Normalized Target Actual
      Redis RPS (pipeline=1, SET) 7,824,532 ops/sec 1,919,289 ops/sec 4.1 50.00% 50.00% +100.00%
      Redis RPS (pipeline=16, SET) 55,025,658 ops/sec 11,728,058 ops/sec 4.6 20.00% 20.00% +36.00%
      PassMark Memory Mark (composite) 2,981 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 137,109 MB/sec 108,466 MB/sec 1.3 10.00% 10.00% +2.70%
      PassMark single-thread CPU 2,642 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,678

      Geekbench Multi-Core

      Score: 17,035

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 81,485
      Compression
      		 1,479,186
      Encryption
      		 109,324
      Extended Instructions
      		 76,636
      Floating Point Maths
      		 242,452
      Integer Maths
      		 441,562
      Physics
      		 7,325
      Prime Numbers
      		 528
      Single Threaded
      		 2,642
      String Sorting
      		 185,840

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,981
      Database Operations
      		 26,783
      Memory Latency
      		 61
      Memory Read Cached
      		 26,471
      Memory Read Uncached
      		 17,964
      Memory Write
      		 17,328

      Stress-ng Raw Scores

      Stress-ng Relative Multicore Performance

      LLM Inference Speed for Prompt Processing

      LLM Inference Speed for Text Generation

      Static Web Server

      Redis

      Alternatives

      Servers of the Same Family

      INSTANCEvCPUsMEMORYAccelerators
      inf2.xlarge 416 GiB0
      inf2.8xlarge 32128 GiB0
      inf2.48xlarge 192768 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      inf2.24xlarge FAQs