logo

inf1.24xlarge by Amazon Web Services

inf1.24xlarge is a AWS Inferentia Gen1 24xlarge server offered by Amazon Web Services with 96 vCPUs, 192 GiB of memory and 0 GB of storage. The pricing starts at 0.4721 USD per hour.
96 vCPU
192 GiB Memory
Spare SCore
94572
(All-cores)
1562
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
inf1.24xlarge
Description
AWS Inferentia Gen1 24xlarge
Family
inf1
Hw Virt
Status
active
Observed At
2026-07-19T06:33:18.122051

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.5918 USD/h 4.721 USD/h
Northern Virgina (US) / us-east-1
1.19878 USD/h 4.721 USD/h
Oregon (US) / us-west-2
1.263825 USD/h 4.721 USD/h
Mumbai (IN) / ap-south-1
0.590967 USD/h 4.965 USD/h
Stockholm (SE) / eu-north-1
1.30815 USD/h 5.016 USD/h
Quebec (CA) / ca-central-1
2.893 USD/h 5.26 USD/h
Dublin (IE) / eu-west-1
1.3163 USD/h 5.26 USD/h
Paris (FR) / eu-west-3
0.70835 USD/h 5.517 USD/h
Milan (IT) / eu-south-1
0.79695 USD/h 5.53 USD/h
London (GB) / eu-west-2
0.807867 USD/h 5.53 USD/h
California (US) / us-west-1
1.09395 USD/h 5.671 USD/h
Seoul (KR) / ap-northeast-2
3.09295 USD/h 5.812 USD/h
Frankfurt (DE) / eu-central-1
2.5953 USD/h 5.902 USD/h
Sydney (AU) / ap-southeast-2
1.018533 USD/h 5.902 USD/h
Cape Town (ZA) / af-south-1
0.629367 USD/h 6.249 USD/h
Tokyo (JP) / ap-northeast-1
4.569033 USD/h 6.376 USD/h
Singapore (SG) / ap-southeast-1
2.915667 USD/h 6.376 USD/h
Hong Kong (HK) / ap-east-1
4.0007 USD/h 7.274 USD/h
Sao Paulo (BR) / sa-east-1
0.78 USD/h 7.8 USD/h

Processor

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
2.5 GHz
CPU Architecture
x86_64
CPU Manufacturer
Intel
CPU Family
Xeon
CPU Model
8275CL
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
1 MiB
CPU L2 Cache Total
48 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
72 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, ss, ht, syscall, nx, pdpe1gb, rdtscp, lm, constant_tsc, arch_perfmon, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, monitor, ssse3, fma, cx16, pcid, sse4_1, sse4_2, x2apic, movbe, popcnt, tsc_deadline_timer, aes, xsave, avx, f16c, rdrand, hypervisor, lahf_lm, abm, 3dnowprefetch, pti, fsgsbase, tsc_adjust, bmi1, avx2, smep, bmi2, erms, invpcid, mpx, avx512f, avx512dq, rdseed, adx, smap, clflushopt, clwb, avx512cd, avx512bw, avx512vl, xsaveopt, xsavec, xgetbv1, xsaves, ida, arat, pku, ospke
Ecpus
60.6
Scalability
126.25

System Resources and Accelerators

MEMORY
Memory Amount
192 GiB
Memory Amount Actual
192 GiB
Memory Generation
DDR4
Memory Speed
2933 Mhz
GPU
GPU Count
0
GPU Memory Min
0 MiB
GPU Memory Total
0 MiB
GPUs
    STORAGE
    Storage Size
    0 GB
    Storages
      NETWORK
      Network Speed Baseline
      100 Gbps
      Network Speed Max
      100 Gbps
      Network Storage Speed Baseline
      19 Gbps
      Network Storage Speed Max
      19 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      A high-core compute instance featuring ninety-six virtual CPUs, fast memory bandwidth, and high-speed networking for demanding multi-threaded workloads.

      Compute OptimizedGeneral Purpose

      Amazon Web Services inf1.24xlarge is an x86_64 server built on the AWS Nitro hypervisor, featuring a dedicated Intel Xeon 8275CL processor with 96 vCPUs and 48 physical cores running at 2.5 GHz. It is configured with 192.0 GB of DDR4 memory, 100 Gbps baseline network bandwidth, zero GPUs, and no local storage. Benchmarks show strong multi-core CPU performance and high memory bandwidth, placing in the top 25% for stress-ng multi-core and Passmark CPU tests. Conversely, text generation for large language models performs in the bottom 10%. With its high vCPU count and 1:2 RAM-to-vCPU ratio, this instance is optimized for compute-heavy workloads, high-throughput static web serving, and Redis database operations that do not require local storage.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      3.06Score
      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) 8,435,271 ops/sec 1,895,838 ops/sec 4.45 50.00% 50.00% +111.00%
      Redis RPS (pipeline=16, SET) 47,539,157 ops/sec 11,497,234 ops/sec 4.13 20.00% 20.00% +32.80%
      PassMark Memory Mark (composite) 2,812 2,410 1.17 10.00% 10.00% +1.58%
      Memory bandwidth (read, 16 MB ~ L3) 242,437 MB/sec 107,331 MB/sec 2.26 10.00% 10.00% +8.50%
      PassMark single-thread CPU 2,186 Mops/s 2,363 Mops/s 0.925 10.00% 10.00% -0.78%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,284

      Geekbench Multi-Core

      Score: 13,044

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		62409
      Compression
      		1328995
      Encryption
      		41648
      Extended Instructions
      		83999
      Floating Point Maths
      		169727
      Integer Maths
      		317154
      Physics
      		5211
      Prime Numbers
      		349
      Single Threaded
      		2186
      String Sorting
      		151153

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		2812
      Database Operations
      		22950
      Memory Latency
      		51
      Memory Read Cached
      		26138
      Memory Read Uncached
      		10774
      Memory Write
      		10344

      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

      INSTANCEvCPUsMEMORYGPUs
      inf1.xlarge 48 GiB0
      inf1.2xlarge 816 GiB0
      inf1.6xlarge 2448 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYGPUs

      inf1.24xlarge FAQs