inf1.6xlarge by Amazon Web Services

inf1.6xlarge is a AWS Inferentia Gen1 6xlarge server offered by Amazon Web Services with 24 vCPUs, 48 GiB of memory and 0 GB of storage. The pricing starts at 0.1254 USD per hour.
24 vCPU
48 GiB Memory
Spare SCore
23,648
(All-cores)
1,496
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
inf1.6xlarge
Description
AWS Inferentia Gen1 6xlarge
Family
inf1
Hw Virt
Status
active
Observed At
2026-11-10T19:17:50.223668

Availability

REGION / IDSPOTONDEMAND
Ohio (US) / us-east-2
0.190533 USD/h 1.18 USD/h
Oregon (US) / us-west-2
0.263425 USD/h 1.18 USD/h
Northern Virgina (US) / us-east-1
0.26022 USD/h 1.18 USD/h
Mumbai (IN) / ap-south-1
0.368033 USD/h 1.241 USD/h
Stockholm (SE) / eu-north-1
0.1254 USD/h 1.254 USD/h
Quebec (CA) / ca-central-1
0.1687 USD/h 1.315 USD/h
Dublin (IE) / eu-west-1
0.375433 USD/h 1.315 USD/h
Paris (FR) / eu-west-3
0.1657 USD/h 1.379 USD/h
London (GB) / eu-west-2
0.148767 USD/h 1.382 USD/h
Milan (IT) / eu-south-1
0.2337 USD/h 1.382 USD/h
California (US) / us-west-1
0.1418 USD/h 1.418 USD/h
Seoul (KR) / ap-northeast-2
0.1453 USD/h 1.453 USD/h
Frankfurt (DE) / eu-central-1
0.360733 USD/h 1.475 USD/h
Sydney (AU) / ap-southeast-2
0.4262 USD/h 1.475 USD/h
Singapore (SG) / ap-southeast-1
0.279133 USD/h 1.594 USD/h
Tokyo (JP) / ap-northeast-1
0.313233 USD/h 1.594 USD/h
Hong Kong (HK) / ap-east-1
0.19565 USD/h 1.819 USD/h
Sao Paulo (BR) / sa-east-1
0.195 USD/h 1.95 USD/h

Processor

vCPUs
24
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
12
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
384 KiB
CPU L1I Cache
32 KiB
CPU L1I Cache Total
384 KiB
CPU L2 Cache
1 MiB
CPU L2 Cache Total
12 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
15.8
Scalability
65.83

System Resources and Accelerators

MEMORY
Memory Amount
48 GiB
Memory Amount Actual
48 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
      25 Gbps
      Network Speed Max
      25 Gbps
      Network Storage Speed Baseline
      4.75 Gbps
      Network Storage Speed Max
      4.75 Gbps
      Inbound Traffic
      0 GB/month
      Outbound Traffic
      0 GB/month
      IPv4
      0

      Server Description

      A dedicated Intel Xeon compute instance with balanced memory performance and high-speed networking for optimized workloads.

      Compute OptimizedGeneral Purpose

      Amazon Web Services inf1.6xlarge is a compute-oriented instance featuring 24 dedicated vCPUs and 48.0 GB of DDR4 memory. Powered by an Intel Xeon 8275CL processor running at 2.5 GHz on the Nitro hypervisor, this x86_64 instance delivers balanced compute performance with a 25 Gbps baseline network speed. It contains no local storage or discrete GPUs. Benchmark results place its CPU and memory performance in the average tier, highlighted by a PassMark CPU score of 23788.28 and a strong PassMark memory score in the top 25%. The instance is suited for web serving, software compilation, and small to medium model inference workloads.

      Economics

      Average Price per Region

      Prices per Zone

      Lowest Prices

      Performance

      Workload Profiles

      1.2Score
      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) 2,339,335 ops/sec 1,922,940 ops/sec 1.2 50.00% 50.00% +9.50%
      Redis RPS (pipeline=16, SET) 14,038,854 ops/sec 11,809,431 ops/sec 1.2 20.00% 20.00% +3.70%
      PassMark Memory Mark (composite) 2,769 2,406 1.2 10.00% 10.00% +1.80%
      Memory bandwidth (read, 16 MB ~ L3) 123,328 MB/sec 108,668 MB/sec 1.1 10.00% 10.00% +0.96%
      PassMark single-thread CPU 2,119 Mops/s 2,365 Mops/s 0.88 10.00% 10.00% -1.30%

      Memory Bandwidth

      Compression

      OpenSSL

      Geekbench Single-Core

      Score: 1,259

      Geekbench Multi-Core

      Score: 9,635

      Passmark CPU Scores

      BENCHMARKSCORE
      Mark
      		 23,788
      Compression
      		 350,516
      Encryption
      		 10,886
      Extended Instructions
      		 24,585
      Floating Point Maths
      		 42,454
      Integer Maths
      		 79,169
      Physics
      		 2,247
      Prime Numbers
      		 118
      Single Threaded
      		 2,119
      String Sorting
      		 40,503

      Passmark Memory Scores

      BENCHMARKSCORE
      Memory Mark
      		 2,769
      Database Operations
      		 8,890
      Memory Latency
      		 50
      Memory Read Cached
      		 25,404
      Memory Read Uncached
      		 11,706
      Memory Write
      		 11,030

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

      Similar Servers

      INSTANCEVENDORvCPUsMEMORYAccelerators

      inf1.6xlarge FAQs