Standard_NC24rs_v3 specs and pricing | Azure

Azure Virtual Machine: NC24rs_v3 / NC24rs v3 with 24 vCPUs and 448 GiB of memory. Available in 25 regions starting from $9,825.80 per month. A -66.12% cheaper alternative is available.

Name	Standard_NC24rs_v3
Details	Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 24 – The number of vCPUs s – Premium Storage capable r – Remote direct memory access (RDMA) capable v3 – version
vCPUs	24
CPU Architecture	x64
Memory (GiB)	448
Hyper-V Generations	V1,V2
ACUs	0
GPUs	4
GPU Name	NVIDIA Tesla V100
GPU RAM (GiB)	16
GPU Total RAM (GiB)	64
Max Network Interfaces	8
RDMA Enabled	yes
Accelerated Net	no

OS Disk Size	1023 GiB
Res Disk Size	2948 GiB
Max Disks	32
Support Premium Disk	yes
Combined IOPS is a sum of all attached disk's IOPs	0
Uncached Disk IOPS	80000

Regional Prices

US Dollar ($)

Per Hour

Standard

Pay-as-you-go

Region Name	Region ID	Linux Price	Windows Price
East US	eastus	13.4600	14.5600
West US 2	westus2	13.4600	14.5680
West US 3	westus3	13.4600	14.5680
hidden-1	hidden-1	13.4640	14.5872
hidden-2	hidden-2	14.5410	15.6450
hidden-3	hidden-3	14.8100	15.9140
hidden-4	hidden-4	14.8104	16.5924
hidden-5	hidden-5	15.2140	16.3180
hidden-6	hidden-6	15.7530	16.8570
hidden-7	hidden-7	15.7920	16.8960
hidden-8	hidden-8	16.1570	17.7760
hidden-9	hidden-9	16.1570	17.7760
hidden-10	hidden-10	16.8210	18.0360
hidden-11	hidden-11	17.5030	18.6070
hidden-12	hidden-12	18.4540	19.5580
hidden-13	hidden-13	18.5030	19.6070
hidden-14	hidden-14	18.5030	19.8400
hidden-15	hidden-15	18.5030	19.6070
hidden-16	hidden-16	18.6300	19.7340
hidden-17	hidden-17	18.6300	19.7340
hidden-18	hidden-18	18.6300	19.7340
hidden-19	hidden-19	18.6300	19.7340
hidden-20	hidden-20	18.6300	19.7340
hidden-21	hidden-21	20.8690	21.9730
hidden-22	hidden-22	26.9280	28.0320

Best AI models you can run on this instance

Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC24rs_v3's 64 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
Gemma 4 26B A4B	Google	25.7#137	26B	4B	62 GB
Qwen3.5 9B	Alibaba	25.0#146	9B	—	22 GB
Gemma 4 12B	Google	22.0#173	12B	—	29 GB
7 more models fit on Standard_NC24rs_v3 Unlock the full ranked list and FP8 / INT4 quantization with a CloudPrice subscription.

Similar Alternative VMs

Find Similar Instances In:

Microsoft Azure