Massed Compute In stock
USA 4 configs 1x-8x
On-Demand
from $0.35
Nvidia A30
Mid-range data center GPU with MIG support for partitioned inference.
Last update 8 minutes ago
Aggregating historical prices...
Key Specifications
A30 Pricing and Availability
For smaller projects, the A30 is available around $0.29/hr per GPU (on-demand). This tier offers a 76% discount compared to the higher end of the market ($1.23/hr).
Heads up: We do our best to keep these specs & prices accurate. However, cloud costs may fluctuate based on region, usage, and other factors not listed here. These are estimates based on common setups and are for informational purposes only. Always verify current rates & exact specs with the provider before provisioning.
Frequently Asked Questions
Why choose the A30?
24GB HBM2e with higher memory bandwidth than GDDR6 alternatives. Supports FP64 for mixed AI and scientific workloads. MIG support for partitioning into smaller instances.
When is the A30 not a good fit?
PCIe-only. 24GB VRAM is limiting for larger models. The L40S offers more VRAM (48GB) and FP8 at a similar price point for pure inference.
Are A30 prices going up or down?
The median on-demand price across providers has risen about 113% since August 2025, from $0.33 to $0.70/hr per GPU. This reflects the market-wide median, which moves both when providers change prices and when lower or higher priced offerings enter the market.
What size AI models can the A30 run?
With 24GB of VRAM, the A30 can typically run 7B to 13B models in FP16, or larger models in 4-bit quantized form.
How much VRAM does the A30 have?
The A30 has 24GB of VRAM. Multi-GPU setups increase total memory, but that memory is not automatically pooled across GPUs.
What is the A30's memory bandwidth?
The A30 has 933 GB/s of memory bandwidth. Higher bandwidth helps with faster data transfer between GPU memory and compute cores.
What data types does the A30 support?
The A30 supports 7 precision formats. Training: BF16, FP16, TF32, FP32. Inference: INT4, INT8. Scientific: FP64.
Does the A30 support NVLink?
No. The A30 is a PCIe-only GPU with no NVLink, so it is better suited to single-GPU inference and smaller-scale workloads than large distributed training jobs.
How much does the A30 cost per hour?
A30 pricing currently ranges from $0.29/hr to $1.23/hr per GPU, depending on the provider, instance type, and billing model.
How much does the A30 cost per month?
At 720 hours per month, one A30 can cost between $208.80 to $883.08 per month, depending on the provider. Reserved and spot pricing can lower that further.
Which cloud providers offer the A30?
The A30 is available from 5 cloud providers, including Exoscale, AceCloud, GPU.ai. Pricing and availability vary by region and billing model.
Can I rent the A30 in the cloud?
Yes. We currently track 16 A30 listings across 5 cloud providers:
Billing type Listings Avg $/GPU/hr On-demand 13 $0.63/hr Reserved 3 $0.71/hr
Technical Specifications
| Peak FP64 | 5.2 TF |
| Peak FP64 Tensor Core | 10.3 TF |
| Peak FP32 | 10.3 TF |
| TF32 Tensor Core | 82 TF, 165 TF* |
| BFLOAT16 Tensor Core | 165 TF, 330 TF* |
| Peak FP16 Tensor Core | 165 TF, 330 TF* |
| Peak INT8 Tensor Core | 330 TOPS, 661 TOPS* |
| Peak INT4 Tensor Core | 661 TOPS, 1321 TOPS* |
| Media engines | 1 optical flow accelerator (OFA), 1 JPEG decoder (NVJPEG), 4 Video decoders (NVDEC) |
| GPU Memory | 24GB HBM2 |
| GPU Memory Bandwidth | 933GB/s |
| Interconnect | PCIe Gen4: 64GB/s, Third-gen NVIDIA® NVLINK® 200GB/s** |
| Form Factor | 2-slot, full height, full length (FHFL) |
| Max thermal design power (TDP) | 165W |
| Multi-Instance GPU (MIG) | 4 MIGs @ 6GB each, 2 MIGs @ 12GB each, 1 MIG @ 24GB |
| Virtual GPU (vGPU) software support | NVIDIA AI Enterprise, NVIDIA Virtual Compute Server |
* With sparsity
** NVLink Bridge for up to two GPUs
Source: official Nvidia A30 datasheet.
Alternatives to Nvidia A30
Last updated