Standard_NC48ads_A100_v4
Azure Virtual Machine: NC48ads_A100_v4 / NC48ads A100_v4 with 48 vCPUs and 440 GiB of memory. Available in 26 regions starting from $5,362.58 per month. A -58.17% cheaper alternative is available.
| Standard_NC48ads_A100_v4 |
| Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 48 – 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 |
| 48 |
| x64 |
| 440 |
| V2 |
| 0 |
| 2 |
| NVIDIA A100 |
| 80 |
| 160 |
| 4 |
| no |
| yes |
| 1023 GiB |
| 128 GiB |
| 16 |
| yes |
| 64000 |
| 60000 |
| 488 MiB/Sec |
| 488 MiB/Sec |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| East US | eastus | 7.3460 | 9.5540 |
| East US 2 | eastus2 | 7.3460 | 9.5540 |
| hidden-1 | hidden-1 | 7.3460 | 9.5540 |
| West US 2 | westus2 | 7.3460 | 9.5540 |
| hidden-2 | hidden-2 | 8.3010 | 10.5090 |
| hidden-3 | hidden-3 | 8.8150 | 11.0230 |
| hidden-4 | hidden-4 | 8.8150 | 11.0230 |
| hidden-5 | hidden-5 | 8.8150 | 11.0230 |
| hidden-6 | hidden-6 | 8.8150 | 11.0230 |
| hidden-7 | hidden-7 | 9.1830 | 11.3910 |
| hidden-8 | hidden-8 | 9.1830 | 11.3910 |
| hidden-10 | hidden-10 | 9.5500 | 11.7580 |
| hidden-11 | hidden-11 | 9.5500 | 11.7580 |
| hidden-12 | hidden-12 | 9.5500 | 11.7580 |
| hidden-13 | hidden-13 | 9.5500 | 11.7580 |
| hidden-14 | hidden-14 | 9.5500 | 11.7580 |
| hidden-15 | hidden-15 | 9.5500 | 11.7580 |
| hidden-16 | hidden-16 | 9.5500 | 11.7580 |
| hidden-9 | hidden-9 | 9.5500 | 11.7580 |
| hidden-17 | hidden-17 | 9.9170 | 12.1250 |
| hidden-18 | hidden-18 | 10.2840 | 12.4920 |
| hidden-19 | hidden-19 | 10.2840 | 12.4920 |
| hidden-20 | hidden-20 | 10.5050 | 12.7130 |
| hidden-21 | hidden-21 | 10.6520 | 12.8600 |
| hidden-22 | hidden-22 | 10.6520 | 12.8600 |
| hidden-23 | hidden-23 | 14.6920 | 16.9000 |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC48ads_A100_v4's 160 GB of GPU memory, assuming the model is sharded across all 2 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 27B |  Alibaba | 37.1#51 | 27B | — | 65 GB | |
| Qwen3.5 27B | Alibaba | 33.8#72 | 27B | — | 65 GB | |
| Qwen3.6 35B A3B | Alibaba | 31.6#91 | 35B | 3B | 84 GB | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure