Standard_NC6s_v3


Azure Virtual Machine: NC6s_v3 / NC6s v3 with 6 vCPUs and 112 GiB of memory. Available in 25 regions starting from $2,233.80 per month. A -72.88% cheaper alternative is available.
NameStandard_NC6s_v3
DetailsStandard is recommended tier
N – GPU enabled
C – High-performance computing and machine learning workloads
6 – The number of vCPUs
s – Premium Storage capable
v3 – version
vCPUs6
CPU Architecturex64
Memory (GiB)112
Hyper-V GenerationsV1,V2
ACUs0
GPUs1
GPU NameNVIDIA Tesla V100
GPU RAM (GiB)16
GPU Total RAM (GiB)16
Max Network Interfaces4
RDMA Enabledno
Accelerated Netyes
OS Disk Size1023 GiB
Res Disk Size736 GiB
Max Disks12
Support Premium Diskyes
Combined IOPS is a sum of all attached disk's IOPs24000
Uncached Disk IOPS20000
Combined Write is a sum of all attached disk's write throughtput201 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput201 MiB/Sec

Regional Prices

US Dollar ($)
Per Hour
Standard
Pay-as-you-go
Region Name
Region ID
Linux Price
Windows Price
East USeastus3.06003.3360
East US 2eastus23.06003.3408
hidden-1hidden-13.06003.3360
West US 2westus23.06003.3360
hidden-2hidden-23.30503.5810
hidden-3hidden-33.36603.6420
hidden-4hidden-43.36603.7708
hidden-5hidden-53.45803.7340
hidden-6hidden-63.58003.8560
hidden-7hidden-73.58903.8650
hidden-8hidden-83.67204.0400
hidden-9hidden-93.67204.0400
hidden-10hidden-103.82304.0990
hidden-11hidden-113.97804.2540
hidden-12hidden-124.19404.4700
hidden-13hidden-134.20504.4810
hidden-14hidden-144.20504.5090
hidden-15hidden-154.20504.4810
hidden-16hidden-164.23404.5100
hidden-17hidden-174.23404.5100
hidden-18hidden-184.23404.5100
hidden-19hidden-194.23404.5100
hidden-20hidden-204.23404.5100
hidden-21hidden-214.74305.0190
hidden-22hidden-226.12006.3960
Activate subscription to see all regions and unlock awesome features  

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC6s_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 4BAlibaba logoAlibaba27.1#1904B10 GB
MiniCPM5 1BOpenbmb18.2#2921B2 GB
MiniCPM5 1B Non-ReasoningOpenbmb17.9#2981B2 GB
7 more models fit on Standard_NC6s_v3
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:
Microsoft Azure