Standard_NC96ads_A100_v4


Azure Virtual Machine: NC96ads_A100_v4 / NC96ads A100_v4 with 96 vCPUs and 880 GiB of memory. Available in 26 regions starting from $10,725.16 per month. A -69.23% cheaper alternative is available.
NameStandard_NC96ads_A100_v4
DetailsStandard is recommended tier
N – GPU enabled
C – High-performance computing and machine learning workloads
96 – The number of vCPUs
A100 – NVIDIA Ampere A100 Accelerator
a – AMD-based processor
d – Diskfull (local temp disk is present)
s – Premium Storage capable
v4 – version
vCPUs96
CPU Architecturex64
Memory (GiB)880
Hyper-V GenerationsV2
ACUs0
GPUs4
GPU NameNVIDIA A100
GPU RAM (GiB)80
GPU Total RAM (GiB)320
Max Network Interfaces8
RDMA Enabledno
Accelerated Netyes
OS Disk Size1023 GiB
Res Disk Size256 GiB
Max Disks32
Support Premium Diskyes
Combined IOPS is a sum of all attached disk's IOPs128000
Uncached Disk IOPS120000
Combined Write is a sum of all attached disk's write throughtput977 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput977 MiB/Sec

Regional Prices

US Dollar ($)
Per Hour
Standard
Pay-as-you-go
Region Name
Region ID
Linux Price
Windows Price
East USeastus14.692019.1080
East US 2eastus214.692019.1080
hidden-1hidden-114.692019.1080
West US 2westus214.692019.1080
hidden-2hidden-216.602021.0180
hidden-3hidden-317.630022.0460
hidden-4hidden-417.630022.0460
hidden-5hidden-517.630022.0460
hidden-6hidden-617.630022.0460
hidden-7hidden-718.365022.7810
hidden-8hidden-818.365022.7810
hidden-10hidden-1019.100023.5160
hidden-11hidden-1119.100023.5160
hidden-12hidden-1219.100023.5160
hidden-13hidden-1319.100023.5160
hidden-14hidden-1419.100023.5160
hidden-15hidden-1519.100023.5160
hidden-16hidden-1619.100023.5160
hidden-9hidden-919.100023.5160
hidden-17hidden-1719.834024.2500
hidden-18hidden-1820.569024.9850
hidden-19hidden-1920.569024.9850
hidden-20hidden-2021.010025.4260
hidden-21hidden-2121.303025.7190
hidden-22hidden-2221.303025.7190
hidden-23hidden-2329.384033.8000
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_NC96ads_A100_v4's 320 GB of GPU memory, assuming the model is sharded across all 4 GPUs. 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
Qwen3.6 27BAlibaba logoAlibaba37.1#4927B—65 GB
Qwen3.5 27BAlibaba logoAlibaba33.8#6927B—65 GB
Qwen3.6 35B A3BAlibaba logoAlibaba33.0#8135B3B84 GB
7 more models fit on Standard_NC96ads_A100_v4
Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:
Microsoft Azure
Select your cookie preferences
We use cookies and similar tools to enhance your experience, provide our services, and make improvements. Approved third parties also use these tools to certain site features. More details available here Cookie Policy