Data center · accelerator
NVIDIA A30
An Ampere compute GPU with 24 GB HBM2 and a 165 W TDP for enterprise servers. MIG can split the GPU into up to four instances for smaller inference or compute jobs.
Technical specifications
| Architecture | NVIDIA Ampere |
|---|---|
| GPU memory | 24 GB HBM2 |
| Memory bandwidth | 933 GB/s |
| Host interface | PCIe Gen4 |
| Maximum TDP | 165 W |
| Form factor | Dual-slot, full-height, full-length |
| NVLink | 200 GB/s; bridge for up to 2 GPUs |
| MIG configurations | 4 x 6 GB / 2 x 12 GB / 1 x 24 GB |
| Media engines | 4 NVDEC, 1 JPEG decoder, 1 OFA |
Applications
- LLM and other neural-network inference.
- Training and fine-tuning neural networks.
- Scientific simulations and GPU-accelerated data analysis.
Compatibility
- Verify the exact server model, slot clearance, power cabling and cooling with the OEM. A PCIe slot alone does not establish compatibility. Passive cooling requires forced airflow from the server.
- MIG partitions share the capacity of one 24 GB GPU; they do not add memory. NVLink is a two-GPU bridge configuration and requires a supported server layout.
- Check driver, CUDA/framework and operating-system support for the intended workload. Virtualization and enterprise software may require separate licenses and a supported host configuration.
Manufacturer sources
Specifications checked against the listed NVIDIA sources: .
Request a quote
Each quote is prepared individually for the selected variant, quantity and destination. The RFQ covers condition, configuration, source, warranty, availability and delivery timing.