inf1.2xlarge by Amazon Web Services

inf1.2xlarge is a AWS Inferentia Gen1 2xlarge server offered by Amazon Web Services with 8 vCPUs, 16 GiB of memory and 0 GB of storage. The pricing starts at 0.0385 USD per hour.
8 vCPU
16 GiB Memory
Spare SCore
7,874
(All-cores)
1,495
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
inf1.2xlarge
Description
AWS Inferentia Gen1 2xlarge
Family
inf1
Hw Virt
Status
active
Observed At
2026-11-05T08:02:26.616741

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.066867 USD/h 0.362 USD/h
Oregon (US) / us-west-2
0.084 USD/h 0.362 USD/h
Northern Virgina (US) / us-east-1
0.10164 USD/h 0.362 USD/h
Mumbai (IN) / ap-south-1
0.1188 USD/h 0.381 USD/h
Stockholm (SE) / eu-north-1
0.0385 USD/h 0.385 USD/h
Quebec (CA) / ca-central-1
0.09205 USD/h 0.403 USD/h
Dublin (IE) / eu-west-1
0.127833 USD/h 0.403 USD/h
Paris (FR) / eu-west-3
0.0984 USD/h 0.423 USD/h
London (GB) / eu-west-2
0.0694 USD/h 0.424 USD/h
Milan (IT) / eu-south-1
0.0818 USD/h 0.424 USD/h
California (US) / us-west-1
0.0858 USD/h 0.435 USD/h
Seoul (KR) / ap-northeast-2
0.06435 USD/h 0.446 USD/h
Frankfurt (DE) / eu-central-1
0.1577 USD/h 0.453 USD/h
Sydney (AU) / ap-southeast-2
0.157533 USD/h 0.453 USD/h
Tokyo (JP) / ap-northeast-1
0.1177 USD/h 0.489 USD/h
Singapore (SG) / ap-southeast-1
0.119367 USD/h 0.489 USD/h
Hong Kong (HK) / ap-east-1
0.06685 USD/h 0.558 USD/h
Sao Paulo (BR) / sa-east-1
0.0598 USD/h 0.598 USD/h

Processor

vCPUs
8
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
4
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
128 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
128 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
4 MiB
CPU L3 Cache
36 MiB
CPU L3 Cache Total
36 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, rep_good, nopl, xtopology, nonstop_tsc, cpuid, aperfmperf, tsc_known_freq, pni, pclmulqdq, 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
5.3
Scalability
66.25

System Resources and Accelerators

MEMORY
Memory Amount
16 GiB
Memory Amount Actual
16 GiB
Memory Generation
DDR4
Memory Speed
2933 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
      5 Gbps
      Network Speed Max
      25 Gbps
      Network Storage Speed Baseline
      1.19 Gbps
      Network Storage Speed Max
      4.75 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      An x86_64 compute instance with dedicated Intel Xeon cores and balanced memory performance for standard web serving and utility workloads.

      Compute OptimizedGeneral Purpose

      Amazon Web Services inf1.2xlarge is an x86_64 server featuring an Intel Xeon 8275CL processor with 8 dedicated vCPUs, 4 physical cores, and 16.0 GB of DDR4 memory. Operating on the AWS Nitro hypervisor, it delivers a baseline network bandwidth of 5 Gbps and lacks local storage. Performance benchmarks indicate average capabilities, with a PassMark CPU score of 8870.98 and a static web serving throughput of 6.88 GB/sec. However, it exhibits weak performance in multi-threaded decompression and LLM inference, with prompt processing for a 7B model dropping to a poor 11.45 tokens/sec. This server is best suited for web serving, moderate database operations, and general compute tasks rather than heavy AI inference workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.49Score
      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) 783,320 ops/sec 1,938,397 ops/sec 0.41 50.00% 50.00% -36.00%
      Redis RPS (pipeline=16, SET) 4,807,518 ops/sec 11,810,473 ops/sec 0.4 20.00% 20.00% -17.00%
      PassMark Memory Mark (composite) 2,194 2,410 0.92 10.00% 10.00% -0.83%
      Memory bandwidth (read, 16 MB ~ L3) 53,994 MB/sec 108,490 MB/sec 0.49 10.00% 10.00% -6.90%
      PassMark single-thread CPU 2,105 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,211

      Geekbench Multi-Core

      Score: 4,565

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 8,871
      Compression
      		 116,356
      Encryption
      		 3,623
      Extended Instructions
      		 6,846
      Floating Point Maths
      		 14,116
      Integer Maths
      		 26,259
      Physics
      		 997
      Prime Numbers
      		 52
      Single Threaded
      		 2,105
      String Sorting
      		 13,725

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,194
      Database Operations
      		 2,987
      Memory Latency
      		 54
      Memory Read Cached
      		 25,435
      Memory Read Uncached
      		 10,861
      Memory Write
      		 10,292

      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
      inf1.xlarge 48 GiB0
      inf1.6xlarge 2448 GiB0
      inf1.24xlarge 96192 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      inf1.2xlarge FAQs