NVIDIA · Ampere
A100 SXM 40 GB rental prices and specifications
Full GPU rental listings; VRAM is nominal hardware capacity. Host-accessible memory can be lower. This profile lists observed rental offers and sourced specifications. Inference benchmarks are shown when available.
Profile checked · Primary source ↗
- Memory
- 40 GB
- Bandwidth
- 1555 GB/s
- Current offers
- 0
- FP16 dense
- 312 TFLOPS
- BF16 dense
- 312 TFLOPS
- FP8 dense
- Not verified
- Interconnect
- Third-generation NVLink up to 600 GB/s; SXM4 / HGX topology depends on system.
Compare A100 SXM 40 GB cloud rentals
Use the exact 40 GB GPU profile when comparing rental quotes. Tables separate currencies, billing periods and rental terms; the required GPU count determines the whole-instance compute cost. Storage, transfer, taxes and other charges can be additional.
Source checks show when each price was actually observed. Historical quotes remain available separately and do not enter current price comparisons. Explore the sourced GPU rental price index or check a rental against your model requirements.
40 GB SXM4 specifications, whitepaper Table 4: boost-clock dense tensor peaks; structural sparsity is excluded. · Specification source 1 ↗
Recently checked listings
Current rental offers
| GPU / provider | Instance price / offer | Terms / location |
|---|---|---|
| No offers match these filters. Try another billing period or currency. | ||
Previously observed offers
427 retained quotes with an old check, a different allocation, or unavailable status. These are excluded from current prices and capacity counts.
Show previously observed offers →Measured performance
Inference benchmarks
| Model | GPU setup | Engine | Quant. | Workload | Reported tok/s | Evidence | Max-load capacity scenarioUSD / million output tokens |
|---|---|---|---|---|---|---|---|
| No benchmark records have been supplied yet. | |||||||