Standard_NG32ads_V620_v1


Azure Virtual Machine: NG32ads_V620_v1 / NG32ads V620_v1 with 32 vCPUs and 64 GiB of memory. Available in 7 regions starting from $1,854.20 per month.
NameStandard_NG32ads_V620_v1
DetailsStandard is recommended tier
N – GPU enabled
32 – The number of vCPUs
V620 – Accelerator Type
a – AMD-based processor
d – Diskfull (local temp disk is present)
s – Premium Storage capable
v1 – version
vCPUs32
CPU Architecturex64
Memory (GiB)64
Hyper-V GenerationsV1,V2
ACUs0
GPUs1
GPU NameAMD Radeon PRO V620 GPU (32GB)
GPU RAM (GiB)32
GPU Total RAM (GiB)32
Max Network Interfaces8
RDMA Enabledno
Accelerated Netyes
OS Disk Size1023 GiB
Res Disk Size1024 GiB
Max Disks32
Support Premium Diskyes
Combined IOPS is a sum of all attached disk's IOPs150000
Uncached Disk IOPS51200
Combined Write is a sum of all attached disk's write throughtput1907 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput1907 MiB/Sec

Regional Prices

US Dollar ($)
Per Hour
Standard
Pay-as-you-go
Region Name
Region ID
Linux Price
Windows Price
East US 2eastus22.54004.0120
West US 3westus32.54004.0120
Central UScentralus3.12004.5920
hidden-1hidden-13.18004.6520
hidden-2hidden-23.30204.7740
hidden-3hidden-33.30204.7740
hidden-4hidden-43.68005.1520
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_NG32ads_V620_v1's 32 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 12BGoogle logoGoogle#23412B—29 GB
Qwen3.5 9BAlibaba logoAlibaba#2399B—22 GB
Qwen3.5 4BAlibaba logoAlibaba#2554B—10 GB
7 more models fit on Standard_NG32ads_V620_v1
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:
Microsoft Azure