Standard_ND40rs_v2
Azure Virtual Machine: ND40rs_v2 / ND40rs v2 with 40 vCPUs and 672 GiB of memory. Available in 8 regions starting from $16,083.36 per month. A -72.55% cheaper alternative is available.
| Standard_ND40rs_v2 |
| Standard is recommended tier N – GPU enabled D – Training and inference scenarios for deep learning 40 – The number of vCPUs s – Premium Storage capable r – Remote direct memory access (RDMA) capable v2 – version |
| 40 |
| x64 |
| 672 |
| V2 |
| 0 |
| 8 |
| NVIDIA Tesla V100 |
| 32 |
| 256 |
| 8 |
| yes |
| yes |
| 1023 GiB |
| 2900 GiB |
| 8 |
| yes |
| 0 |
| 80000 |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| East US | eastus | 22.0320 | 23.8720 |
| West US 2 | westus2 | 22.0320 | 23.8720 |
| hidden-1 | hidden-1 | 26.4380 | 28.2780 |
| hidden-2 | hidden-2 | 27.5260 | 29.3660 |
| hidden-3 | hidden-3 | 27.5400 | 29.3790 |
| hidden-4 | hidden-4 | 27.5400 | 29.3790 |
| hidden-5 | hidden-5 | 30.4920 | 32.3320 |
| Sweden Central | swedencentral | n/a | 23.8720 |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_ND40rs_v2's 256 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 | |
|---|---|---|---|---|---|---|
| Qwen3.6 27B |  Alibaba | 37.1#53 | 27B | — | 65 GB | |
| Qwen3.5 27B | Alibaba | 33.8#75 | 27B | — | 65 GB | |
| Qwen3.6 35B A3B | Alibaba | 31.6#94 | 35B | 3B | 84 GB | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure