dl1.24xlarge by Amazon Web Services

dl1.24xlarge is a Deep Learning Gen1 24xlarge server offered by Amazon Web Services with 96 vCPUs, 768 GiB of memory and 4 TB of storage. The pricing starts at 13.109 USD per hour.
96 vCPU
768 GiB Memory
4 TB Storage
8 GPU
Spare SCore
94,567
(All-cores)
1,569
(Single-core)

Specifications

Server Metadata

Vendor ID
aws
Name
dl1.24xlarge
Description
Deep Learning Gen1 24xlarge
Family
dl1
Hw Virt
Status
active
Observed At
2026-09-19T02:45:05.724080

Availability

REGION / IDSPOTONDEMAND
Oregon (US) / us-west-2
13.109 USD/h -

Processor

vCPUs
96
Hypervisor
nitro
CPU Allocation
Dedicated
CPU Cores
48
CPU Speed
3 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, avx512_vnni
Ecpus
60.3
Scalability
125.62

System Resources and Accelerators

MEMORY
Memory Amount
768 GiB
Memory Amount Actual
768 GiB
Memory Generation
DDR4
Memory Speed
2933 Mhz
GPU
GPU Count
8
GPU Memory Min
32 GiB
GPU Memory Total
256 GiB
GPU Manufacturer
Habana
GPU Family
Gaudi
GPU Model
HL-205
GPUs
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
  • Habana Gaudi HL-205 (Memory amount: 32768)
STORAGE
Storage Size
4000 GB
Storage Type
nvme ssd
Storages
  • 1000 GB nvme ssd
  • 1000 GB nvme ssd
  • 1000 GB nvme ssd
  • 1000 GB nvme ssd
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 specialized accelerator platform combining eight dedicated GPUs, high-capacity system memory, and fast local NVMe storage for parallel computing.

GPU AcceleratedCompute OptimizedStorage & Database

Amazon Web Services dl1.24xlarge is a GPU-accelerated instance designed for deep learning and parallel computing workloads. Powered by 96 vCPUs from Intel Xeon 8275CL processors at 3.0 GHz, it features 768.0 GB of DDR4 memory and eight Habana Gaudi HL-205 GPUs providing 256 GB of total VRAM. Storage is supported by 4000 GB of local NVMe SSDs, and networking delivers a 100 Gbps baseline. Benchmarks indicate strong multi-core CPU performance, with a stress-ng multi-core score of 94566.82, and strong memory bandwidth of up to 5249.26 GB/sec. While single-core performance is average, the instance delivers strong results in database operations and software compilation. This hardware profile is optimized for deep learning training, multi-threaded data processing, and high-throughput database workloads.

Economics

Average Price per Region

Prices per Zone

Lowest Prices

Performance

Workload Profiles

3.02Score
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) 8,417,091 ops/sec 1,919,696 ops/sec 4.38 50.00% 50.00% +109.00%
Redis RPS (pipeline=16, SET) 48,204,065 ops/sec 11,736,081 ops/sec 4.11 20.00% 20.00% +32.70%
PassMark Memory Mark (composite) 2,781 2,418 1.15 10.00% 10.00% +1.41%
Memory bandwidth (read, 16 MB ~ L3) 230,864 MB/sec 108,260 MB/sec 2.13 10.00% 10.00% +7.85%
PassMark single-thread CPU 2,205 Mops/s 2,365 Mops/s 0.932 10.00% 10.00% -0.70%

Memory Bandwidth

Compression

OpenSSL

Geekbench Single-Core

Score: 1,385

Geekbench Multi-Core

Score: 13,509

Passmark CPU Scores

BENCHMARKSCORE
Mark
 62653
Compression
 1330179
Encryption
 41086
Extended Instructions
 85226
Floating Point Maths
 169673
Integer Maths
 317122
Physics
 5191
Prime Numbers
 366
Single Threaded
 2205
String Sorting
 150131

Passmark Memory Scores

BENCHMARKSCORE
Memory Mark
 2781
Database Operations
 23361
Memory Latency
 52
Memory Read Cached
 26630
Memory Read Uncached
 10439
Memory Write
 10183

Stress-ng Raw Scores

Stress-ng Relative Multicore Performance

Static Web Server

Redis

Alternatives

Servers of the Same Family

INSTANCEvCPUsMEMORYGPUs

Similar Servers

INSTANCEVENDORvCPUsMEMORYGPUs

dl1.24xlarge FAQs