Standard_ND96asr_v4
Azure Virtual Machine: ND96asr_v4 / ND96asr v4 with 96 vCPUs and 900 GiB of memory. Available in 6 regions starting from $19,853.81 per month. A -83.38% cheaper alternative is available.
| Standard_ND96asr_v4 |
| Standard is recommended tier N – GPU enabled D – Training and inference scenarios for deep learning 96 – The number of vCPUs a – AMD-based processor s – Premium Storage capable r – Remote direct memory access (RDMA) capable v4 – version |
| 96 |
| x64 |
| 900 |
| V2 |
| 0 |
| 8 |
| NVIDIA A100 (40GB) |
| 40 |
| 320 |
| 8 |
| yes |
| yes |
| 1023 GiB |
| 2900 GiB |
| 16 |
| yes |
| 0 |
| 80000 |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| East US | eastus | 27.1970 | 31.6130 |
| West US 2 | westus2 | 27.1970 | 31.6130 |
| South Central US | southcentralus | 32.6300 | 37.0460 |
| hidden-1 | hidden-1 | 34.0030 | n/a |
| hidden-2 | hidden-2 | 35.3570 | 39.7730 |
| hidden-3 | hidden-3 | 35.3570 | 39.7730 |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_ND96asr_v4's 320 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#51 | 27B | — | 65 GB | |
| Qwen3.5 27B | Alibaba | 33.8#71 | 27B | — | 65 GB | |
| Qwen3.6 35B A3B | Alibaba | 33.0#83 | 35B | 3B | 84 GB | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure