ND40rs_v2 is a NDSv2 family [RDMA capable] [Premium Storage capable] [Intel processor] 40 vCPUs server offered by Microsoft Azure with 40 vCPUs, 672 GiB of memory and 2.97 TB of storage. The pricing starts at 4.0715 USD per hour.
An accelerated virtual machine featuring eight dedicated GPUs, massive system memory, and low-latency RDMA networking for high-performance computing workloads.
GPU AcceleratedMemory OptimizedStorage & Database
Microsoft Azure ND40rs_v2 is an NDSv2-family virtual machine optimized for GPU-accelerated workloads and high-performance computing. Built on an Intel x86_64 architecture and managed by Microsoft Hyper-V, it features 40 dedicated vCPUs and 672.0 GB of system memory, yielding 16.8 GB of RAM per core. The server is equipped with eight NVIDIA V100 GPUs providing a total of 238 GB of VRAM, alongside 2970 GB of local storage. With support for Premium Storage and RDMA networking, this instance is designed for clustered, high-throughput environments. The hardware profile makes it highly suitable for deep learning training, complex scientific simulations, and memory-intensive database operations.
Economics
Average Price per Region
Prices per Zone
Lowest Prices
Workload Profiles
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.
Precomputed compound score for CI/CD Build 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% Geekbench Clang compilation (multi-core), 10% Geekbench Clang compilation (single-core), 20% stress-ng div16 best-N cores, 5% PassMark integer math, 5% PassMark compression, 5% Brotli compression (multi-core, level 0), 5% PassMark string sorting. Rationale for component selection: Build performance is mainly driven by multi-core compilation throughput, but also bundles single-core compilation speed and general CPU performance, multi-core compression and text/scripting processing.
Precomputed compound score for Compute Heavy Applications 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: 15% stress-ng div16 best-N cores, 10% stress-ng div16 single core, 20% PassMark CPU Mark (composite), 10% Memory bandwidth (read, 64 MB), 15% PassMark floating point, 15% PassMark AVX/SSE/FMA (SIMD), 10% PassMark integer math, 5% PassMark physics simulation. Rationale for component selection: Number-crunching workload augmenting raw CPU performance stressing, general CPU performance benchmarks, memory bandwidth, and pure math computation speed like floating point, integer, SIMD (AVX/SSE/FMA) operations.
Precomputed compound score for Data Analysis 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: 70% PassMark CPU Mark (composite), 10% Gzip compression (single-core, level 5), 10% Memory bandwidth (read, 64 MB), 10% PassMark Memory Mark (composite). Rationale for component selection: Data analysis and ETL workloads are memory-bandwidth-bound and CPU-throughput-driven. The profile combines general CPU performance and memory bandwidth/latency as the primary drivers, supplemented by single-core compression speed as a proxy for serialisation-heavy ETL tasks.
Precomputed compound score for LLM Inference 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: 15% LLM text generation (SmolLM-135M, 128 tok), 15% LLM prompt processing (SmolLM-135M, 512 tok), 15% LLM text generation (Llama 7B, 128 tok), 15% LLM prompt processing (Llama 7B, 512 tok), 15% LLM text generation (Llama-3.3 70B, 128 tok), 15% LLM prompt processing (Llama-3.3 70B, 512 tok), 5% Memory bandwidth (read, 256 MB), 2% PassMark AVX/SSE/FMA (SIMD), 2% PassMark floating point. Rationale for component selection: VRAM and memory-bandwidth-bound LLM inference workload, using direct LLM speed benchmarks at three model sizes, and supplementing with raw memory bandwidth and SIMD performance benchmarks.
Precomputed compound score for Web Server 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: 30% Static web RPS (1 KiB, 8 conn/vCPU), 20% Static web RPS (64 KiB, 8 conn/vCPU), 20% Static web throughput (256 KiB, 8 conn/vCPU), 20% OpenSSL AES-256-CBC (16 kB blocks), 5% Gzip compression (multi-core, level 5), 5% PassMark string sorting. Rationale for component selection: Primary workloads drivers are single-process static HTTP serving speed and throughput, text processing, TLS termination, and asset compression.
Alternatives
Servers of the Same Family
INSTANCE
vCPUs
MEMORY
GPUs
Similar Servers
INSTANCE
VENDOR
vCPUs
MEMORY
GPUs
ND40rs_v2 FAQs
ND40rs_v2 is a NDSv2 family [RDMA capable] [Premium Storage capable] [Intel processor] 40 vCPUs server offered by Microsoft Azure with 40 vCPUs, 672 GiB of memory and 2.97 TB of storage. The pricing starts at 4.0715 USD per hour.
The ND40rs_v2 server is equipped with 40 logical CPU cores on unknown number of physical CPU core(s), 672 GiB of memory, 2.97 TB of storage, and 8 V100 GPUs. Additional block storage can be attached as needed.
The pricing for ND40rs_v2 servers starts at 4.0715 USD per hour, but the actual price depends on the selected region, zone and server allocation method (e.g. on-demand versus spot pricing options): currently, we track the prices in 30 regions and zones every 5 minutes, and the maximum price stands at 30.492 USD.
The ND40rs_v2 server is offered by Microsoft Azure, founded in 2010, headquartered in Washington, United States. For more information, visit the Microsoft Azure homepage.
The ND40rs_v2 server is available in 30 availability zones of the following 5 regions: East US (US), West US 2 (US), South Central US (US), West Europe (NL), Southeast Asia (SG).
An accelerated virtual machine featuring eight dedicated GPUs, massive system memory, and low-latency RDMA networking for high-performance computing workloads.
