Standard_NC64as_T4_v3
Azure Virtual Machine: NC64as_T4_v3 / NC64as T4_v3 with 64 vCPUs and 440 GiB of memory. Available in 30 regions starting from $3,176.96 per month. A -29.39% cheaper alternative is available.
| Standard_NC64as_T4_v3 |
| Standard is recommended tier N – GPU enabled C – High-performance computing and machine learning workloads 64 – The number of vCPUs T4 – NVIDIA Tesla T4 Accelerator a – AMD-based processor s – Premium Storage capable v3 – version |
| 64 |
| x64 |
| 440 |
| V1,V2 |
| 0 |
| 4 |
| NVIDIA T4 |
| 16 |
| 64 |
| 8 |
| no |
| yes |
| 1023 GiB |
| 2816 GiB |
| 32 |
| yes |
| 16320 |
| 48000 |
| 240 MiB/Sec |
| 240 MiB/Sec |
Regional Prices
Region Name | Region ID | Linux Price | Windows Price |
|---|---|---|---|
| East US | eastus | 4.3520 | 7.2960 |
| East US 2 | eastus2 | 4.3520 | 7.2960 |
| hidden-1 | hidden-1 | 4.3520 | 7.2960 |
| hidden-2 | hidden-2 | 4.3520 | 7.2960 |
| North Central US | northcentralus | 4.3520 | 7.2960 |
| hidden-3 | hidden-3 | 4.6030 | 7.5470 |
| hidden-4 | hidden-4 | 4.7870 | 7.7310 |
| hidden-5 | hidden-5 | 4.8200 | 7.7640 |
| hidden-6 | hidden-6 | 4.8530 | 7.7970 |
| hidden-7 | hidden-7 | 4.9070 | 7.8510 |
| hidden-8 | hidden-8 | 5.0770 | 8.0210 |
| hidden-9 | hidden-9 | 5.0810 | 8.0250 |
| hidden-10 | hidden-10 | 5.0920 | 8.0360 |
| hidden-11 | hidden-11 | 5.2110 | 8.1550 |
| hidden-12 | hidden-12 | 5.2220 | 8.1660 |
| hidden-13 | hidden-13 | 5.2220 | 8.1660 |
| hidden-14 | hidden-14 | 5.3530 | 8.2970 |
| hidden-15 | hidden-15 | 5.4160 | 8.3600 |
| hidden-16 | hidden-16 | 5.4280 | 8.3720 |
| hidden-17 | hidden-17 | 5.4400 | 8.3840 |
| hidden-18 | hidden-18 | 5.4400 | 8.3840 |
| hidden-19 | hidden-19 | 5.6450 | 8.5890 |
| hidden-20 | hidden-20 | 5.6450 | 8.5890 |
| hidden-21 | hidden-21 | 5.6580 | 8.6020 |
| hidden-22 | hidden-22 | 5.8750 | 8.8190 |
| hidden-23 | hidden-23 | 5.9770 | 8.9210 |
| hidden-24 | hidden-24 | 6.0890 | 9.0330 |
| hidden-25 | hidden-25 | 6.1230 | 9.0670 |
| hidden-26 | hidden-26 | 6.3410 | 9.2850 |
| hidden-27 | hidden-27 | 7.3830 | 10.3270 |
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in Standard_NC64as_T4_v3's 64 GB of GPU memory, assuming the model is sharded across all 4 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 | |
|---|---|---|---|---|---|---|
| Gemma 4 26B A4B |  Google | 25.7#135 | 26B | 4B | 62 GB | |
| Qwen3.5 9B |  Alibaba | 25.0#144 | 9B | — | 22 GB | |
| Gemma 4 12B | Google | 22.0#171 | 12B | — | 29 GB | |
Similar Alternative VMs
Find Similar Instances In:
Microsoft Azure