Standard_NV12s_v2
Azure Virtual Machine: NV12s_v2 / NV12s v2 with 12 vCPUs and 224 GiB of memory. Available in 2 regions starting from $998.64 per month.
| Standard_NV12s_v2 |
| Standard is recommended tier N – GPU enabled V – Remote visualisation workloads and other graphics-intensive applications 12 – The number of vCPUs s – Premium Storage capable v2 – version |
| 12 |
| x64 |
| 224 |
| V1,V2 |
| 0 |
| 2 |
| NVIDIA Tesla M60 |
| 8 |
| 16 |
| 8 |
| no |
| no |
| 1023 GiB |
| 1474 GiB |
| 24 |
| yes |
| 48000 |
| 40000 |
| 500 MiB/Sec |
| 500 MiB/Sec |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| South Central US | southcentralus | 1.3680 | 1.6440 |
| West US | westus | 1.5340 | 1.8100 |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_NV12s_v2's 16 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 | |
|---|---|---|---|---|---|---|
| Qwen3.5 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 | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure