Standard_NCC40ads_H100_v5
Azure Virtual Machine: NCC40ads_H100_v5 / NCC40ads H100_v5 with 40 vCPUs and 320 GiB of memory. Available in 4 regions starting from $5,095.40 per month.
| Standard_NCC40ads_H100_v5 |
| Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 40 – The number of vCPUs H100 – Accelerator Type a – AMD-based processor d – Diskfull (local temp disk is present) s – Premium Storage capable v5 – version |
| 40 |
| x64 |
| 320 |
| V2 |
| 0 |
| 1 |
| NVIDIA H100 |
| 94 |
| 752 |
| 8 |
| no |
| no |
| 1023 GiB |
| 1024 GiB |
| 8 |
| yes |
| 32000 |
| 30000 |
| 244 MiB/Sec |
| 244 MiB/Sec |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| East US 2 | eastus2 | 6.9800 | n/a |
| Central US | centralus | 7.8900 | n/a |
| South Central US | southcentralus | 9.7300 | n/a |
| hidden-1 | hidden-1 | 10.7400 | n/a |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_NCC40ads_H100_v5's 752 GB of GPU memory. 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 | |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash |  DeepSeek | 40.3#31 | 158B | — | 379 GB | |
| MiniMax M2.7 |  MiniMax | 38.1#45 | 229B | — | 549 GB | |
| Qwen3.6 27B |  Alibaba | 37.1#54 | 27B | — | 65 GB | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure