Standard_NC8as_T4_v3 specs and pricing | Azure

Azure Virtual Machine: NC8as_T4_v3 / NC8as T4_v3 with 8 vCPUs and 56 GiB of memory. Available in 30 regions starting from $548.96 per month.

Name	Standard_NC8as_T4_v3
Details	Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 8 – The number of vCPUs T4 – NVIDIA Tesla T4 Accelerator a – AMD-based processor s – Premium Storage capable v3 – version
vCPUs	8
CPU Architecture	x64
Memory (GiB)	56
Hyper-V Generations	V1,V2
ACUs	0
GPUs	1
GPU Name	NVIDIA T4
GPU RAM (GiB)	16
GPU Total RAM (GiB)	16
Max Network Interfaces	8
RDMA Enabled	no
Accelerated Net	yes

OS Disk Size	1023 GiB
Res Disk Size	352 GiB
Max Disks	16
Support Premium Disk	yes
Combined IOPS is a sum of all attached disk's IOPs	32000
Uncached Disk IOPS	48000
Combined Write is a sum of all attached disk's write throughtput	480 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput	480 MiB/Sec

Regional Prices

US Dollar ($)

Per Hour

Standard

Pay-as-you-go

Region Name	Region ID	Linux Price	Windows Price
East US	eastus	0.7520	1.1200
East US 2	eastus2	0.7520	1.1200
hidden-1	hidden-1	0.7520	1.1200
hidden-2	hidden-2	0.7520	1.1200
North Central US	northcentralus	0.7520	1.1200
hidden-3	hidden-3	0.7960	1.1640
hidden-4	hidden-4	0.8270	1.1950
hidden-5	hidden-5	0.8340	1.2020
hidden-6	hidden-6	0.8380	1.2060
hidden-7	hidden-7	0.8490	1.2170
hidden-8	hidden-8	0.8780	1.2460
hidden-9	hidden-9	0.8790	1.2470
hidden-10	hidden-10	0.8800	1.2480
hidden-11	hidden-11	0.9020	1.2700
hidden-12	hidden-12	0.9020	1.2700
hidden-13	hidden-13	0.9020	1.2700
hidden-14	hidden-14	0.9250	1.2930
hidden-15	hidden-15	0.9370	1.3050
hidden-16	hidden-16	0.9390	1.3070
hidden-17	hidden-17	0.9400	1.3080
hidden-18	hidden-18	0.9400	1.3080
hidden-19	hidden-19	0.9770	1.3450
hidden-20	hidden-20	0.9770	1.3450
hidden-21	hidden-21	0.9780	1.3460
hidden-22	hidden-22	1.0150	1.3830
hidden-23	hidden-23	1.0340	1.4020
hidden-24	hidden-24	1.0520	1.4200
hidden-25	hidden-25	1.0590	1.4270
hidden-26	hidden-26	1.0970	1.4650
hidden-27	hidden-27	1.2770	1.6450

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC8as_T4_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#190	4B	—	10 GB
MiniCPM5 1B	Openbmb	12.0#291	1B	—	2 GB
MiniCPM5 1B Non-Reasoning	Openbmb	11.7#299	1B	—	2 GB
7 more models fit on Standard_NC8as_T4_v3 Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:

Microsoft Azure