inf1.xlarge by Amazon Web Services

inf1.xlarge is a AWS Inferentia Gen1 xlarge server offered by Amazon Web Services with 4 vCPUs, 8 GiB of memory and 0 GB of storage. The pricing starts at 0.0228 USD per hour.
4 vCPU
8 GiB Memory
Spare SCore
3,930
(All-cores)
1,491
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
inf1.xlarge
Description
AWS Inferentia Gen1 xlarge
Family
inf1
Hw Virt
Status
active
Observed At
2026-09-18T17:00:16.336124

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.0271 USD/h 0.228 USD/h
Oregon (US) / us-west-2
0.0535 USD/h 0.228 USD/h
Northern Virgina (US) / us-east-1
0.05484 USD/h 0.228 USD/h
Mumbai (IN) / ap-south-1
0.064 USD/h 0.24 USD/h
Stockholm (SE) / eu-north-1
0.0242 USD/h 0.242 USD/h
Quebec (CA) / ca-central-1
0.05415 USD/h 0.254 USD/h
Dublin (IE) / eu-west-1
0.074467 USD/h 0.254 USD/h
Milan (IT) / eu-south-1
0.0392 USD/h 0.267 USD/h
London (GB) / eu-west-2
0.0404 USD/h 0.267 USD/h
Paris (FR) / eu-west-3
0.0503 USD/h 0.267 USD/h
California (US) / us-west-1
0.05705 USD/h 0.274 USD/h
Seoul (KR) / ap-northeast-2
0.03645 USD/h 0.281 USD/h
Sydney (AU) / ap-southeast-2
0.089033 USD/h 0.285 USD/h
Frankfurt (DE) / eu-central-1
0.0887 USD/h 0.285 USD/h
Cape Town (ZA) / af-south-1
- 0.302 USD/h
Singapore (SG) / ap-southeast-1
0.0633 USD/h 0.308 USD/h
Tokyo (JP) / ap-northeast-1
0.071033 USD/h 0.308 USD/h
Hong Kong (HK) / ap-east-1
0.04795 USD/h 0.352 USD/h
Sao Paulo (BR) / sa-east-1
0.0413 USD/h 0.377 USD/h

Processor

vCPUs
4
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
2
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
64 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
64 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
2 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
2.6
Scalability
130

System Resources and Accelerators

MEMORY
Memory Amount
8 GiB
Memory Amount Actual
8 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
      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 entry-level dedicated compute instance featuring Intel Xeon processors and balanced single-core performance for lightweight workloads.

      Compute OptimizedGeneral Purpose

      Amazon Web Services inf1.xlarge is an x86_64 instance in the inf1 family, powered by an Intel Xeon 8275CL processor running at 2.5 GHz. It features 4 dedicated vCPUs across 2 physical cores, 8.0 GB of DDR4 memory, and a baseline network bandwidth of 5 Gbps, with no local storage or discrete GPUs. Benchmark data shows average single-core CPU performance in stress-ng and gzip compression, alongside weak multi-core performance and low memory bandwidth. The instance achieves an average text generation speed of 75.74 tokens per second for small language models. Qualitatively, the inf1.xlarge provides a budget-friendly entry point for dedicated compute resources. It is appropriate for lightweight single-threaded applications, basic web serving, and small-scale machine learning inference tasks that do not demand high memory capacity or local storage.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      0.268Score
      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) 382,379 ops/sec 1,919,696 ops/sec 0.199 50.00% 50.00% -55.40%
      Redis RPS (pipeline=16, SET) 2,452,061 ops/sec 11,736,081 ops/sec 0.209 20.00% 20.00% -26.90%
      PassMark Memory Mark (composite) 1,115 2,418 0.461 10.00% 10.00% -7.45%
      Memory bandwidth (read, 16 MB ~ L3) 37,193 MB/sec 108,260 MB/sec 0.344 10.00% 10.00% -10.10%
      PassMark single-thread CPU 2,104 Mops/s 2,365 Mops/s 0.89 10.00% 10.00% -1.16%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,149

      Geekbench Multi-Core

      Score: 2,526

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 4625
      Compression
      		 58936
      Encryption
      		 1810
      Extended Instructions
      		 3378
      Floating Point Maths
      		 7054
      Integer Maths
      		 13146
      Physics
      		 603
      Prime Numbers
      		 29
      Single Threaded
      		 2104
      String Sorting
      		 6989

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 1115
      Database Operations
      		 1520
      Memory Latency
      		 52
      Memory Read Cached
      		 25410
      Memory Read Uncached
      		 11334
      Memory Write
      		 10617

      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
      inf1.2xlarge 816 GiB0
      inf1.6xlarge 2448 GiB0
      inf1.24xlarge 96192 GiB0

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYGPUs

      inf1.xlarge FAQs