Standard_ND96isr_H200_v5
Azure Virtual Machine: ND96isr_H200_v5 / ND96isr H200_v5 with 96 vCPUs and 1850 GiB of memory. Available in 30 regions starting from $61,904.00 per month.
| Standard_ND96isr_H200_v5 |
| Standard is recommended tier N – GPU enabled D – Training and inference scenarios for deep learning 96 – The number of vCPUs H200 – Accelerator Type i – Isolated size s – Premium Storage capable r – Remote direct memory access (RDMA) capable v5 – version |
| 96 |
| x64 |
| 1850 |
| V2 |
| 0 |
| 8 |
| NVIDIA H200 GPU (141GB) |
| 141 |
| 1128 |
| 8 |
| yes |
| yes |
| 1023 GiB |
| 1024 GiB |
| 16 |
| yes |
| 0 |
| 80000 |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| East US 2 | eastus2 | 84.8000 | 89.2160 |
| West US 2 | westus2 | 84.8000 | 89.2160 |
| West US 3 | westus3 | 84.8000 | 89.2160 |
| hidden-1 | hidden-1 | 93.2800 | 97.6960 |
| hidden-2 | hidden-2 | 95.8240 | 100.2400 |
| hidden-3 | hidden-3 | 99.2160 | 103.6320 |
| hidden-4 | hidden-4 | 99.2160 | 103.6320 |
| hidden-5 | hidden-5 | 101.7600 | 106.1760 |
| hidden-6 | hidden-6 | 101.7600 | 106.1760 |
| hidden-10 | hidden-10 | 106.0000 | 110.4160 |
| hidden-11 | hidden-11 | 106.0000 | 110.4160 |
| hidden-12 | hidden-12 | 106.0000 | 110.4160 |
| hidden-7 | hidden-7 | 106.0000 | 110.4160 |
| hidden-8 | hidden-8 | 106.0000 | 110.4160 |
| hidden-9 | hidden-9 | 106.0000 | 110.4160 |
| hidden-13 | hidden-13 | 110.2400 | 114.6560 |
| hidden-14 | hidden-14 | 110.2400 | 114.6560 |
| hidden-15 | hidden-15 | 110.2400 | 114.6560 |
| hidden-16 | hidden-16 | 110.2400 | 114.6560 |
| hidden-17 | hidden-17 | 110.2400 | 114.6560 |
| hidden-18 | hidden-18 | 110.2400 | 114.6560 |
| hidden-19 | hidden-19 | 110.2720 | 114.6880 |
| hidden-20 | hidden-20 | 111.0880 | 115.5040 |
| hidden-21 | hidden-21 | 121.2640 | 125.6800 |
| hidden-22 | hidden-22 | 121.2640 | 125.6800 |
| hidden-23 | hidden-23 | 122.9600 | 127.3760 |
| hidden-24 | hidden-24 | 123.8080 | 128.2240 |
| hidden-25 | hidden-25 | 130.5920 | 135.0080 |
| hidden-26 | hidden-26 | 131.4400 | 135.8560 |
| hidden-27 | hidden-27 | 169.6000 | 174.0160 |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_ND96isr_H200_v5's 1128 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 | |
|---|---|---|---|---|---|---|
| MiniMax M3 |  MiniMax | 44.4#15 | 427B | — | 1025 GB | |
| DeepSeek V4 Flash |  DeepSeek | 40.3#28 | 158B | — | 379 GB | |
| MiMo V2.5 424B |  Xiaomi | 40.1#32 | 424B | — | 1018 GB | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure