Standard_NV12s_v3 specs and pricing | Azure

Azure Virtual Machine: NV12s_v3 / NV12s v3 with 12 vCPUs and 112 GiB of memory. Available in 21 regions starting from $832.20 per month. A -27.19% cheaper alternative is available.

Name	Standard_NV12s_v3
Details	Standard is recommended tier N – GPU enabled V – Remote visualisation workloads and other graphics-intensive applications 12 – The number of vCPUs s – Premium Storage capable v3 – version
vCPUs	12
CPU Architecture	x64
Memory (GiB)	112
Hyper-V Generations	V1,V2
ACUs	0
GPUs	1
GPU Name	NVIDIA Tesla M60 (16GB)
GPU RAM (GiB)	16
GPU Total RAM (GiB)	16
Max Network Interfaces	4
RDMA Enabled	no
Accelerated Net	yes

OS Disk Size	1023 GiB
Res Disk Size	736 GiB
Max Disks	12
Support Premium Disk	yes
Combined IOPS is a sum of all attached disk's IOPs	24000
Uncached Disk IOPS	20000
Combined Write is a sum of all attached disk's write throughtput	201 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput	201 MiB/Sec

Regional Prices

US Dollar ($)

Per Hour

Standard

Pay-as-you-go

Region Name	Region ID	Linux Price	Windows Price
East US	eastus	1.1400	1.6920
East US 2	eastus2	1.1400	1.6920
hidden-1	hidden-1	1.1400	1.6920
West US	westus	1.1400	1.6920
hidden-2	hidden-2	1.2100	1.7620
hidden-3	hidden-3	1.3680	1.9200
hidden-4	hidden-4	1.3910	1.9430
hidden-5	hidden-5	1.4250	1.9770
hidden-6	hidden-6	1.4250	1.9770
hidden-7	hidden-7	1.4250	1.9770
hidden-8	hidden-8	1.4250	1.9770
hidden-9	hidden-9	1.4260	1.9780
hidden-10	hidden-10	1.4600	2.0120
hidden-11	hidden-11	1.5680	2.1200
hidden-12	hidden-12	1.5690	2.1210
hidden-13	hidden-13	1.5800	2.1320
hidden-14	hidden-14	1.5900	2.1420
hidden-15	hidden-15	1.5900	2.1420
hidden-16	hidden-16	1.5960	2.1480
hidden-17	hidden-17	1.9380	2.4900
hidden-18	hidden-18	2.0380	2.5900

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NV12s_v3's 16 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
Qwen3.5 4B	Alibaba	20.1#192	4B	—	10 GB
MiniCPM5 1B	Openbmb	12.0#293	1B	—	2 GB
MiniCPM5 1B Non-Reasoning	Openbmb	11.7#301	1B	—	2 GB
7 more models fit on Standard_NV12s_v3 Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:

Microsoft Azure