a4x-highgpu-4g
GCP a4x-highgpu-4g - Accelerator Optimized: 4 NVIDIA GB200 GPU, 140 vCPUs, 884GB RAM. Available in 0 regions starting from $0.00 per month.
| a4x-highgpu-4g |
| Optimized for accelerated high performance computing workloads. a – Accelerator optimized 4 – Generation highgpu – High amound of GPU memory - 40x RAM/GPU ratio 4g – Number of GPUs |
| Accelerator optimized |
| Accelerator Optimized: 4 NVIDIA GB200 GPU, 140 vCPUs, 884GB RAM |
| 140 |
| 884 GiB |
| arm64 |
| NVIDIA Grace |
| no |
| yes |
| 4 |
| nvidia-gb200 |
| 744 |
| no |
| no |
| no |
| no |
| no |
| 128 |
| 524288 GB |
| NVMe |
| yes |
| 12000 GB |
| no |
| yes |
| no |
| gVNIC, MRDMA |
Regional Availability
North America
California / us-west2
Iowa / us-central1
Mexico / northamerica-south1
Nevada / us-west4
Ohio / us-east5
Ontario / northamerica-northeast2
Oregon / us-west1
Québec / northamerica-northeast1
South Carolina / us-east1
Texas / us-south1
Utah / us-west3
Virginia / us-east4
California / us-west2
Iowa / us-central1
Mexico / northamerica-south1
Nevada / us-west4
Ohio / us-east5
Ontario / northamerica-northeast2
Oregon / us-west1
Québec / northamerica-northeast1
South Carolina / us-east1
Texas / us-south1
Utah / us-west3
Virginia / us-east4
Europe
Belgium / europe-west1
England / europe-west2
Finland / europe-north1
France / europe-west9
Germany / europe-west10
Germany / europe-west3
Italy / europe-west12
Italy / europe-west8
Netherlands / europe-west4
Poland / europe-central2
Spain / europe-southwest1
Sweden / europe-north2
Switzerland / europe-west6
Belgium / europe-west1
England / europe-west2
Finland / europe-north1
France / europe-west9
Germany / europe-west10
Germany / europe-west3
Italy / europe-west12
Italy / europe-west8
Netherlands / europe-west4
Poland / europe-central2
Spain / europe-southwest1
Sweden / europe-north2
Switzerland / europe-west6
APAC
Australia / australia-southeast1
Australia / australia-southeast2
Hong Kong / asia-east2
India / asia-south1
India / asia-south2
Indonesia / asia-southeast2
Japan / asia-northeast1
Japan / asia-northeast2
Singapore / asia-southeast1
South Korea / asia-northeast3
Taiwan / asia-east1
Australia / australia-southeast1
Australia / australia-southeast2
Hong Kong / asia-east2
India / asia-south1
India / asia-south2
Indonesia / asia-southeast2
Japan / asia-northeast1
Japan / asia-northeast2
Singapore / asia-southeast1
South Korea / asia-northeast3
Taiwan / asia-east1
Middle East
Israel / me-west1
Qatar / me-central1
Saudi Arabia / me-central2
Israel / me-west1
Qatar / me-central1
Saudi Arabia / me-central2
Africa
South Africa / africa-south1
South Africa / africa-south1
South America
Brazil / southamerica-east1
Chile / southamerica-west1
Brazil / southamerica-east1
Chile / southamerica-west1
Regional Prices
Geography | Region Name | Region | Savings Options | Instance Price | |
|---|---|---|---|---|---|
| No matching records found | |||||
Best AI models you can run on this instance
Top open-weight chat models ranked by Intelligence Index that fit in a4x-highgpu-4g's 744 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 | |
|---|---|---|---|---|---|---|
| DeepSeek V4 Flash |  DeepSeek | 40.3#28 | 158B | — | 379 GB | |
| MiniMax M2.7 |  MiniMax | 38.1#42 | 229B | — | 549 GB | |
| Qwen3.6 27B |  Alibaba | 37.1#51 | 27B | — | 65 GB | |
Similar Alternative Instances
Find Similar Instances In:
Instance Type | Region | vCPUs | Memory (GiB) | Instance Price | Price Diff % |
|---|---|---|---|---|---|
| a2-highgpu-4g | Iowa (us-central1) | 48 | 340 | 14.6935 | null% |
| a2-ultragpu-4g | Iowa (us-central1) | 48 | 680 | 20.1108 | null% |
| a3-highgpu-2g | Iowa (us-central1) | 52 | 468 | 21.9581 | null% |
| a3-highgpu-4g | Iowa (us-central1) | 104 | 936 | 43.9162 | null% |