Standard_ND96amsr_A100_v4 specs and pricing | Azure

Azure Virtual Machine: ND96amsr_A100_v4 / ND96amsr A100_v4 with 96 vCPUs and 1800 GiB of memory. Available in 29 regions starting from $23,922.10 per month. A -69.09% cheaper alternative is available.

Name	Standard_ND96amsr_A100_v4
Details	Standard is recommended tier N – GPU enabled D – Training and inference scenarios for deep learning 96 – The number of vCPUs A100 – NVIDIA Ampere A100 Accelerator a – AMD-based processor m – The most amount of memory in a particular size s – Premium Storage capable r – Remote direct memory access (RDMA) capable v4 – version
vCPUs	96
CPU Architecture	x64
Memory (GiB)	1800
Hyper-V Generations	V2
ACUs	0
GPUs	8
GPU Name	NVIDIA A100 (80GB)
GPU RAM (GiB)	80
GPU Total RAM (GiB)	640
Max Network Interfaces	8
RDMA Enabled	yes
Accelerated Net	yes

OS Disk Size	1023 GiB
Res Disk Size	2900 GiB
Max Disks	16
Support Premium Disk	yes
Combined IOPS is a sum of all attached disk's IOPs	1464000
Uncached Disk IOPS	80000
Combined Write is a sum of all attached disk's write throughtput	9216 MiB/Sec
Combined Read is a sum of all attached disk's read throughtput	9830 MiB/Sec

Regional Prices

US Dollar ($)

Per Hour

Standard

Pay-as-you-go

Region Name	Region ID	Linux Price	Windows Price
East US	eastus	32.7700	37.1860
East US 2	eastus2	32.7700	37.1860
hidden-1	hidden-1	32.7700	37.1860
West US 2	westus2	32.7700	37.1860
hidden-2	hidden-2	37.0300	41.4460
hidden-3	hidden-3	39.3240	43.7400
hidden-4	hidden-4	39.3240	43.7400
hidden-5	hidden-5	39.3240	43.7400
hidden-10	hidden-10	40.9620	45.3780
hidden-11	hidden-11	40.9620	45.3780
hidden-6	hidden-6	40.9620	45.3780
hidden-7	hidden-7	40.9620	45.3780
hidden-8	hidden-8	40.9620	45.3780
hidden-9	hidden-9	40.9620	45.3780
hidden-12	hidden-12	42.6010	47.0170
hidden-13	hidden-13	42.9290	47.3450
hidden-14	hidden-14	46.8610	51.2770
hidden-15	hidden-15	46.8610	51.2770
hidden-16	hidden-16	46.8610	51.2770
hidden-17	hidden-17	46.8900	51.3060
hidden-18	hidden-18	47.5160	51.9320
hidden-19	hidden-19	47.5170	51.9330
hidden-20	hidden-20	47.8440	52.2600
hidden-21	hidden-21	49.4830	53.8990
hidden-22	hidden-22	50.7940	55.2100
hidden-23	hidden-23	55.3810	59.7970
hidden-24	hidden-24	60.9190	65.3350
hidden-25	hidden-25	60.9190	65.3350
hidden-26	hidden-26	65.5400	69.9560

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_ND96amsr_A100_v4's 640 GB of GPU memory, assuming the model is sharded across all 8 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
MiniMax M2.7	MiniMax	49.6#32	229B	—	549 GB
DeepSeek V4 Flash	DeepSeek	46.5#48	158B	—	379 GB
Qwen3.6 27B	Alibaba	45.8#51	27B	—	65 GB
7 more models fit on Standard_ND96amsr_A100_v4 Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:

Microsoft Azure