inf2.8xlarge by Amazon Web Services

inf2.8xlarge is a AWS Inferentia Gen2 8xlarge server offered by Amazon Web Services with 32 vCPUs, 128 GiB of memory and 0 GB of storage. The pricing starts at 0.1968 USD per hour.
32 vCPU
128 GiB Memory
Spare SCore
47,852
(All-cores)
2,991
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
inf2.8xlarge
Description
AWS Inferentia Gen2 8xlarge
Family
inf2
Hw Virt
Status
active
Observed At
2026-10-30T01:01:11.047152

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.2999 USD/h 1.9679 USD/h
Northern Virgina (US) / us-east-1
0.436125 USD/h 1.9679 USD/h
Oregon (US) / us-west-2
0.58515 USD/h 1.9679 USD/h
Stockholm (SE) / eu-north-1
0.2165 USD/h 2.1646 USD/h
Dublin (IE) / eu-west-1
0.772333 USD/h 2.4598 USD/h
Sydney (AU) / ap-southeast-2
1.66185 USD/h 2.5582 USD/h
Mumbai (IN) / ap-south-1
0.76815 USD/h 2.5582 USD/h
Paris (FR) / eu-west-3
0.40335 USD/h 2.755 USD/h
Singapore (SG) / ap-southeast-1
1.68565 USD/h 2.755 USD/h
London (GB) / eu-west-2
0.4344 USD/h 2.9518 USD/h
Frankfurt (DE) / eu-central-1
0.7297 USD/h 2.9518 USD/h
Tokyo (JP) / ap-northeast-1
2.9518 USD/h 2.9518 USD/h
Sao Paulo (BR) / sa-east-1
0.3345 USD/h 3.3454 USD/h

Processor

vCPUs
32
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
16
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
512 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
512 KiB
CPU L2 Cache
512 KiB
CPU L2 Cache Total
8 MiB
CPU L3 Cache
32 MiB
CPU L3 Cache Total
64 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, 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, 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
16
Scalability
50

System Resources and Accelerators

MEMORY
Memory Amount
128 GiB
Memory Amount Actual
128 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
      16.667 Gbps
      Network Speed Max
      25 Gbps
      Network Storage Speed Baseline
      10 Gbps
      Network Storage Speed Max
      10 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      A dedicated AMD EPYC virtual server with balanced memory and strong single-core performance for general-purpose computing and moderate inference workloads.

      General PurposeCompute Optimized

      Amazon Web Services inf2.8xlarge is a Nitro-based virtual server featuring 32 dedicated vCPUs and 128.0 GB of DDR4 memory. Powered by an AMD EPYC 7R13 processor running at 3.6 GHz, this x86_64 instance delivers strong single-core CPU performance and encryption capabilities, alongside average multi-core and memory bandwidth metrics. It lacks local storage and discrete GPUs, presenting a tradeoff for data-intensive or hardware-accelerated tasks. Qualitatively, the instance offers a balanced resource profile suitable for general-purpose applications. It is well-suited for web serving, database operations, software compilation, and moderate CPU-based language model inference.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      1.4Score
      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) 2,863,752 ops/sec 1,919,289 ops/sec 1.5 50.00% 50.00% +22.00%
      Redis RPS (pipeline=16, SET) 20,071,151 ops/sec 11,728,058 ops/sec 1.7 20.00% 20.00% +11.00%
      PassMark Memory Mark (composite) 2,878 2,416 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 79,144 MB/sec 108,466 MB/sec 0.72 10.00% 10.00% -3.20%
      PassMark single-thread CPU 2,645 Mops/s 2,365 Mops/s 1.1 10.00% 10.00% +0.96%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,686

      Geekbench Multi-Core

      Score: 13,860

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 41,970
      Compression
      		 557,525
      Encryption
      		 37,953
      Extended Instructions
      		 33,147
      Floating Point Maths
      		 80,773
      Integer Maths
      		 147,258
      Physics
      		 4,058
      Prime Numbers
      		 204
      Single Threaded
      		 2,645
      String Sorting
      		 74,749

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,878
      Database Operations
      		 14,151
      Memory Latency
      		 61
      Memory Read Cached
      		 26,588
      Memory Read Uncached
      		 17,494
      Memory Write
      		 17,577

      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
      inf2.24xlarge 96384 GiB0
      inf2.48xlarge 192768 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      inf2.8xlarge FAQs