Standard_NC32ads_A10_v4 specs and pricing | Azure

Azure Virtual Machine: NC32ads_A10_v4 / NC32ads A10_v4 with 32 vCPUs and 400 GiB of memory. Available in 3 regions starting from $3,212.00 per month.

Name	Standard_NC32ads_A10_v4
Details	Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 32 – The number of vCPUs A10 – Accelerator Type a – AMD-based processor d – Diskfull (local temp disk is present) s – Premium Storage capable v4 – version
vCPUs	32
CPU Architecture	x64
Memory (GiB)	400
Hyper-V Generations	V1,V2
ACUs	0
GPUs	2
GPU Name	NVIDIA A10
GPU RAM (GiB)	24
GPU Total RAM (GiB)	96
Max Network Interfaces	8
RDMA Enabled	no
Accelerated Net	yes

OS Disk Size	1023 GiB
Res Disk Size	2880 GiB
Max Disks	32
Support Premium Disk	yes
Combined IOPS is a sum of all attached disk's IOPs	150000
Uncached Disk IOPS	51200
Combined Write is a sum of all attached disk's write throughtput	1907 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput	1907 MiB/Sec

Regional Prices

US Dollar ($)

Per Hour

Standard

Pay-as-you-go

Region Name	Region ID	Linux Price	Windows Price
West US 3	westus3	4.4000	5.8720
South Central US	southcentralus	5.2800	6.7520
West Europe	westeurope	5.7200	7.1920

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC32ads_A10_v4's 96 GB of GPU memory, assuming the model is sharded across all 2 GPUs. VRAM is estimated from the parameter count at the selected quantization, so treat it as guidance rather than a guarantee.

Chat Models

FP16 (full precision)

Model	Creator	Intelligence	Total params	Active params	~VRAM
Qwen3.6 27B	Alibaba	37.1#70	27B	—	65 GB
Qwen3.5 27B	Alibaba	33.8#94	27B	—	65 GB
Qwen3.6 35B A3B	Alibaba	31.6#113	35B	3B	84 GB
7 more models fit on Standard_NC32ads_A10_v4 Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:

Microsoft Azure