A30 vs A10
Manufacturer specifications of the A30 and the A10, side by side, per GPU. A value the manufacturer does not publish for the exact model is marked as such, never estimated.
NVIDIA A30 24GB
Ampere
- GPU memory
- 24 GB
- Memory bandwidth
- 933 GB/s
Live price on EverXCloud · No offer right now
Suited workloads
NVIDIA A10 24GB
Ampere
- GPU memory
- 24 GB
- Memory bandwidth
- 600 GB/s
Live price on EverXCloud · from $0.24 per GPU-hour
Suited workloads
Key differences
- Both have 24 GB of GPU memory.
- The A30 has 1.6× the memory bandwidth of the A10 (933 vs 600 GB/s), which usually sets the pace of LLM token generation.
- The A30 has 1.3× the dense BF16 tensor throughput of the A10 (165 vs 125 TFLOPS), the precision of most training runs.
- The A10 has ray-tracing cores for 3D rendering; the A30 does not.
Specifications
| Specification | A30 | A10 |
|---|---|---|
| GPU memory | 24 GB | 24 GB |
| Memory type | HBM2 | GDDR6 |
| Memory bandwidth | 933 GB/s (higher) | 600 GB/s |
| FP16 tensor | 165 TFLOPS (higher) | 125 TFLOPS |
| BF16 tensor | 165 TFLOPS (higher) | 125 TFLOPS |
| Max power | 165 W | 150 W |
| Architecture | Ampere | Ampere |
| Interconnect | NVLink bridge (200 GB/s) · PCIe 4.0 | PCIe 4.0 |
The higher value of each measured row is shown in bold. Manufacturer specifications, per GPU. Tensor throughput is shown without sparsity. Values the manufacturer does not publish for this exact model are left out.
What fits in memory, on one GPU
| Workload | A30 | A10 |
|---|---|---|
| LLM inference, 16-bit | ≈ 9B parameters | ≈ 9B parameters |
| LLM inference, 4-bit | ≈ 30B parameters | ≈ 30B parameters |
| Full training, mixed precision | ≈ 1B parameters | ≈ 1B parameters |
Cautious estimates counting 80% of memory for model weights; context length, batch size and framework change the real limit. Several GPUs together hold larger models.
A30 vs A10: frequently asked questions
Which has more memory, the A30 or the A10?
Both have 24 GB of GPU memory.
Which is faster for LLM inference, the A30 or the A10?
Generating tokens is usually bound by memory bandwidth, and the A30 has 1.6× the bandwidth of the A10. Memory size then decides which models fit. Measure your own model before a large run.
Can I rent the A30 and the A10 by the hour?
Yes, when sellers list them on the EverXCloud spot exchange: you buy GPU hours at the live price from a prepaid balance in euros, US dollars or pounds. Prices are shown excluding tax and EverXCloud is the merchant of record for every rental.
Be ready on launch day
Create your account now: you can top up your balance and rent the GPU that fits your workload as soon as the market opens.
Have GPU servers?
Businesses can join the EverXCloud Network and sell hours of their GPU servers on the spot exchange.