Standard_NC16ads_A10_v4 specs and pricing | Azure

Azure Virtual Machine: NC16ads_A10_v4 / NC16ads A10_v4 with 16 vCPUs and 200 GiB of memory. Available in 3 regions starting from $1,606.00 per month.

Name	Standard_NC16ads_A10_v4
Details	Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 16 – 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	16
CPU Architecture	x64
Memory (GiB)	200
Hyper-V Generations	V1,V2
ACUs	0
GPUs	1
GPU Name	NVIDIA A10
GPU RAM (GiB)	24
GPU Total RAM (GiB)	48
Max Network Interfaces	4
RDMA Enabled	no
Accelerated Net	yes

OS Disk Size	1023 GiB
Res Disk Size	1440 GiB
Max Disks	16
Support Premium Disk	yes
Combined IOPS is a sum of all attached disk's IOPs	75000
Uncached Disk IOPS	25600
Combined Write is a sum of all attached disk's write throughtput	954 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput	954 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	2.2000	2.9360
South Central US	southcentralus	2.6400	3.3760
West Europe	westeurope	2.8600	3.5960

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC16ads_A10_v4's 48 GB of GPU memory. 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
Gemma 4 12B	Google	22.0#193	12B	—	29 GB
Qwen3.5 9B	Alibaba	21.4#198	9B	—	22 GB
Apriel V1.5 15B Thinker	Servicenow	21.2#202	15B	—	36 GB
7 more models fit on Standard_NC16ads_A10_v4 Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:

Microsoft Azure