Standard_NG16ads_V620_v1


Azure Virtual Machine: NG16ads_V620_v1 / NG16ads V620_v1 with 16 vCPUs and 32 GiB of memory. Available in 7 regions starting from $927.10 per month.
NameStandard_NG16ads_V620_v1
DetailsStandard is recommended tier
N – GPU enabled
16 – The number of vCPUs
V620 – Accelerator Type
a – AMD-based processor
d – Diskfull (local temp disk is present)
s – Premium Storage capable
v1 – version
vCPUs16
CPU Architecturex64
Memory (GiB)32
Hyper-V GenerationsV1,V2
ACUs0
GPUs1
GPU NameAMD Radeon PRO V620 GPU (32GB)
GPU RAM (GiB)16
GPU Total RAM (GiB)16
Max Network Interfaces4
RDMA Enabledno
Accelerated Netyes
OS Disk Size1023 GiB
Res Disk Size512 GiB
Max Disks16
Support Premium Diskyes
Combined IOPS is a sum of all attached disk's IOPs75000
Uncached Disk IOPS25600
Combined Write is a sum of all attached disk's write throughtput954 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput954 MiB/Sec

Regional Prices

US Dollar ($)
Per Hour
Standard
Pay-as-you-go
Region Name
Region ID
Linux Price
Windows Price
East US 2eastus21.27002.0060
West US 3westus31.27002.0060
Central UScentralus1.56002.2960
hidden-1hidden-11.59002.3260
hidden-2hidden-21.65102.3870
hidden-3hidden-31.65102.3870
hidden-4hidden-41.84002.5760
Activate subscription to see all regions and unlock all features

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NG16ads_V620_v1'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 4BAlibaba logoAlibaba#2554B—10 GB
Granite 4.2 3BIBM logoIBM#3323B—7 GB
MiniCPM5 1BOpenbmb#3681B—2 GB
7 more models fit on Standard_NG16ads_V620_v1
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:
Microsoft Azure