NVIDIA A100 80GB SXM: specs, pricing and what it can run
The previous generation workhorse. No FP8, so modern quantised serving stacks give up a large fraction of their advantage here.
Specifications
| Spec | NVIDIA A100 80GB SXM |
|---|---|
| Architecture | Ampere |
| Released | 2020 |
| Memory | 80 GB HBM2e |
| Memory bandwidth | 2,039 GB/s |
| Dense FP16 | 312 TFLOPS |
| FP8 tensor cores | No |
| Board power | 400 W |
| Interconnect | NVLink 3.0 (600 GB/s) |
| Segment | datacenter |
What fits in 80 GB
Weights only, at 85% of nominal capacity to leave room for the KV cache and activations. Long-context serving needs materially more headroom than this table implies.
| Quantisation | Largest model (weights only) |
|---|---|
| FP16 | ~36B parameters |
| FP8 / INT8 | ~73B parameters |
| 4-bit | ~146B parameters |
Rental cost
Indicative on-demand pricing runs roughly $0.80–$2.20 per GPU-hour depending on provider, region, and commitment. Spot and reserved capacity sit well below that band. These are ranges rather than quotes: street prices move week to week, so check live cloud price feed before budgeting.