Specifications Compared
| Spec | A40 | B200 |
|---|---|---|
| TDP | 300W | 1000W |
| VRAM | 48 GB | 180-192 GB |
| CUDA Cores | 10,752 | 18,432 |
| FP4 (dense) | Not published | 9,000 TFLOPS |
| FP8 (dense) | Not published | 4,500 TFLOPS |
| Memory Type | GDDR6 | HBM3e |
| Architecture | Ampere | Blackwell |
| FP16 (dense) | 149.7 TFLOPS | 2,250 TFLOPS |
| Form Factors | PCIe | SXM, NVL |
| INT8 (dense) | 299.3 TOPS | 4,500 TOPS |
| Interconnect | NVLink, PCIe 4.0 | NVLink, PCIe 6.0, InfiniBand |
| Tensor Cores | 336 | 576 |
| FP32 Performance | 37.4 TFLOPS | 75 TFLOPS |
| FP64 Performance | Not published | 37 TFLOPS |
| Memory Bandwidth | 696 GB/s | 8,000 GB/s |
| FP4 (with sparsity) | Not published | 18,000 TFLOPS |
| FP8 (with sparsity) | Not published | 9,000 TFLOPS |
| FP16 (with sparsity) | 299.4 TFLOPS | 4,500 TFLOPS |
| INT8 (with sparsity) | 598.6 TOPS | 9,000 TOPS |
Performance Analysis
The FP16 dense performance of the B200 at 2250 TFLOPS exceeds the A40 dense FP16 at 149.7 TFLOPS by a factor of 15. This delta allows the B200 to complete training iterations faster for models that utilize dense FP16 computations. Inference tasks also benefit from the higher dense FP16 rate on the B200. Memory bandwidth on the B200 reaches 8000 GB/s compared to 696 GB/s on the A40. This higher bandwidth supports larger batch sizes during both training and inference on the B200. The A40 with its 48 GB VRAM limits batch sizes more than the 180 to 192 GB on the B200.
Current On-Demand Offers
Cheapest secure on-demand offer per provider that is reported in stock right now, per GPU per hour; multi-GPU instances show the whole-instance price alongside. Deploy opens the DeployGPU console for providers on the platform, otherwise the provider's own site. Stock is rechecked every minute.
A40
| Provider | Region | GPUs | Per GPU / hr | Instance / hr | Deploy |
|---|---|---|---|---|---|
| LeaderGPU | The Netherlands | 8 | $0.52 | $4.13 | Deploy |
| RunPod | global | 1 | $0.59 | — | Deploy |
2 providers in stock, 2 offers. All A40 offers, price history and alerts
Notify me when A40 drops below a price
One email when the cheapest in-stock on-demand price per GPU-hour falls below your threshold. Cheapest right now: $0.52/GPU-hr.
QuantaCloud
Comparing B-series options? Get one quote for all of them.
Skip the per-provider sales calls. Reserved and cluster B-series configurations from 16 to 1024+ GPUs with InfiniBand fabric, 3 to 12 month terms. One quote at partner rates, 24h turnaround.
When to Choose the A40
The A40 suits scenarios with power constraints because it operates at 300W TDP. Workloads that require only 48 GB of memory and do not exceed 149.7 TFLOPS dense FP16 find the A40 adequate without the higher power draw of 1000W on the B200.
When to Choose the B200
The B200 fits use cases involving large scale models that need 180 to 192 GB VRAM. Its 2250 TFLOPS dense FP16 enables faster processing of complex computations compared to the A40.
Use Cases
The B200 offers 2250 TFLOPS dense FP16 which accelerates training compared to 149.7 TFLOPS on the A40.
The B200 delivers 2250 TFLOPS dense FP16 along with 8000 GB/s bandwidth to support larger batch sizes than the A40.
The B200 provides 2250 TFLOPS dense FP16 and 180 to 192 GB VRAM for handling fine-tuning of bigger models than the A40 allows.
The A40 supplies 149.7 TFLOPS dense FP16 at 300W TDP for workloads that fit within 48 GB VRAM without excess power consumption.
The A40 provides 37.4 TFLOPS FP32 while the B200 provides 75 TFLOPS FP32 so selection depends on model size requirements.
Frequently Asked Questions
How does FP16 performance differ between the A40 and B200?▾
The A40 achieves 149.7 TFLOPS dense FP16 while the B200 achieves 2250 TFLOPS dense FP16. The B200 also reaches 4500 TFLOPS with sparsity compared to 299.4 TFLOPS with sparsity on the A40.
What memory configurations distinguish the A40 from the B200?▾
The A40 includes 48 GB GDDR6 memory with 696 GB/s bandwidth. The B200 includes 180 to 192 GB HBM3e memory with 8000 GB/s bandwidth.
Which GPU has higher power consumption the A40 or B200?▾
The A40 operates at 300W TDP. The B200 operates at 1000W TDP.
How does FP32 performance compare on the A40 versus the B200?▾
The A40 delivers 37.4 TFLOPS FP32. The B200 delivers 75 TFLOPS FP32.
What interconnect options exist for the A40 and B200?▾
The A40 supports NVLink and PCIe 4.0. The B200 supports NVLink along with PCIe 6.0 and InfiniBand.
How do INT8 capabilities compare between these GPUs?▾
The A40 reaches 299.3 TOPS dense INT8 and 598.6 TOPS with sparsity. The B200 reaches 4500 TOPS dense INT8 and 9000 TOPS with sparsity.
Which is cheaper to rent, the A40 or the B200?▾
Cloud rental prices for both the A40 and B200 vary by provider, configuration, and availability. This page shows live pricing from 25+ providers updated every 60 seconds. Scroll to the Live Cloud Pricing section to compare current rates.
How much VRAM does the A40 have compared to the B200?▾
The A40 has 48 GB of GDDR6 memory. The B200 has 180 to 192 GB of HBM3e memory.
Can I find A40 and B200 GPUs available to rent right now?▾
Yes. This page shows real-time availability across 25+ cloud GPU providers. The Live Cloud Pricing section displays only in-stock offers with current pricing.
What is the main difference between the A40 and the B200?▾
The A40 uses the Ampere architecture (2020) while the B200 uses Blackwell (2024). The B200 delivers 15.0x the dense FP16 throughput (2,250 vs 149.7 TFLOPS, both without sparsity) and 11.5x the memory bandwidth of the A40.
Rent these GPUs
Each GPU page lists every current on-demand offer by provider, per GPU-hour, updated every minute.
Related comparisons
How this page is made
- Specifications come from the NVIDIA, AMD and Intel datasheets for the A40 and the B200. Dense and sparse throughput are listed separately.
- Prices and availability are live: every offer shown is an in-stock, on-demand listing from a provider we track, rechecked every minute.
- The written comparison (overview, performance notes, when to choose each card, verdict, use cases and FAQ) was drafted with an AI model from the specification table above and passed an automated check that rejects any figure not in that table. It was last generated on . It contains no prices; those are always read live.
- Read how we collect the data, or report an error on this page.
Next steps
- Rent A40Every current offer by provider, daily price history and a price alert.
- Rent B200Every current offer by provider, daily price history and a price alert.
- GPU price indexHow on-demand prices for the major GPUs have moved, updated daily.
- All GPUsEvery GPU we track, with current lows and provider counts.