Quick Insights
Performance/Dollar
18.70 TFLOPS/$k
FP16 performance per $1000
VRAM/Dollar
12.0 GB/$k
VRAM per $1000
vs Data Center Average
-58% perf
FP16 TFLOPS comparison
Cloud Availability
3 providers
from $0.400/hr
Specifications
| VRAM | 48GB GDDR6 |
| Memory Bandwidth | 696 GB/s |
| FP16 TFLOPS | 74.8 |
| Tensor TFLOPS | 150.0 |
| FP32 TFLOPS | 37.4 |
| TDP | 300W |
| Form Factor | PCIe |
| Architecture | Ampere |
| NVLink | No |
| Release Date | 2020-10 |
Buy vs Rent Analysis
Buy Hardware
$4.0k
- One-time cost, unlimited usage
- Full control over hardware
- Electricity & cooling costs extra
- Depreciation over 2-3 years
Best if using >10000 hours total
Rent Cloud GPU
$0.400/hr
- Pay only for what you use
- No upfront investment
- Scale up/down instantly
- No maintenance required
Best for <10000 hours or variable usage
Breakeven Point
10,000
hours of usage
At $0.400/hr cloud pricing, buying the hardware pays off after 10,000 hours (~417 days or 13.9 months of 24/7 usage).
| Usage | Monthly Cloud Cost | Months to Breakeven |
|---|---|---|
| 100 hrs/month | $40.00 | 100 months |
| 200 hrs/month | $80.00 | 50 months |
| 500 hrs/month | $200.00 | 20 months |
Cloud GPU Pricing
Rent NVIDIA A40 from 3 cloud providers. Prices shown per GPU per hour.
| Provider | Type | Instance | GPUs | On-Demand | Per GPU | Spot | Availability |
|---|---|---|---|---|---|---|---|
| RunPod | gpu-cloud | NVIDIA A40 | 1x | $0.400/hr | $0.400/hr Cheapest | $0.200/hr (-50%) | - |
| Paperspace | gpu-cloud | paperspace-a40 | 1x | $0.800/hr | $0.800/hr | - | - |
| CoreWeave | gpu-cloud | coreweave-a40 | 1x | $1.04/hr | $1.04/hr | - | - |
Best Spot Deal:
RunPod
offers spot pricing at $0.200/hr
(50% off on-demand).
A40 vs Alternatives
Compare NVIDIA A40 with similar GPUs from other brands.
| GPU | VRAM | FP16 TFLOPS | Bandwidth | Hardware Price | Cloud Price | |
|---|---|---|---|---|---|---|
| A40 Current | 48GB | 74.8 | 696 GB/s | $4.0k | - | - |
| AMD Instinct MI210 AMD | 64GB (+33%) | 181.0 (+142%) | 1.6 TB/s | - | - | Compare |
| AMD Instinct MI100 AMD | 32GB (-33%) | 184.6 (+147%) | 1.2 TB/s | - | - | Compare |
| AMD Radeon RX 7900 XTX AMD | 24GB (-50%) | 122.0 (+63%) | 960 GB/s | - | - | Compare |
Best Use Cases
No specific use case recommendations for NVIDIA A40 yet.
Browse All Use Cases →Compare A40
Alternatives
- AMD Instinct MI210 64GB · -
- AMD Instinct MI100 32GB · -
- AMD Radeon RX 7900 XTX 24GB · -