Compare · prices checked 2026-09-03
RTX 5090 vs A100 SXM4: specs, price per hour, which to rent
NVIDIA RTX 5090 (32 GB, $0.318/hr) against NVIDIA A100 SXM4 (80 GB, $0.583/hr): public specs side by side, live fixed prices from our sheet, what fits in each card's VRAM, and a verdict written for real workloads — both are rentable right now.
RTX 5090 vs A100 SXM4 specifications
Public NVIDIA figures (dense, non-sparsity). The last column is RTX 5090 relative to A100 SXM4.
| Spec | RTX 5090 | A100 SXM4 | Difference |
|---|---|---|---|
| Architecture | Blackwell (2025) | Ampere (2020) | — |
| VRAM | 32 GB GDDR7 | 80 GB HBM2e | −60% |
| Memory bandwidth | 1,792 GB/s | 2,039 GB/s | −12% |
| FP16 tensor (dense) | 419 TFLOPS | 312 TFLOPS | +34% |
| FP32 | 104.8 TFLOPS | 19.5 TFLOPS | +437% |
| CUDA cores | 21,760 | 6,912 | +215% |
| TDP | 575 W | 400 W | +44% |
| PCIe · NVLink | Gen 5.0 · no NVLink | Gen 4.0 · NVLink | — |
| PowerScore (RTX 3090 = 100) | 295 | 220 | +34% |
| Max GPUs per machine | 8× | 8× | — |
RTX 5090 vs A100 SXM4 price per hour
Fixed rates from our sheet — every on-demand price is the marketplace median × 0.70, rounded down. Monthly = 730 hours.
| Rate | RTX 5090 | A100 SXM4 | Cheaper |
|---|---|---|---|
| On-demand, per GPU-hour | $0.318 | $0.583 | RTX 5090 (−45%) |
| Interruptible, per GPU-hour | $0.159 | $0.291 | RTX 5090 |
| Reserved (3 mo), per GPU-hour | $0.206 | $0.378 | RTX 5090 |
| On-demand, per month | $232 | $426 | RTX 5090 |
| Market median (reference) | $0.45 | $0.83 | — |
| $ per 1,000 FP16 TFLOP-hours | $0.76 | $1.87 | RTX 5090 (better value) |
| $ per GB of VRAM per hour | $0.0099 | $0.0073 | A100 SXM4 (better value) |
Try a full month with storage and bandwidth in the GPU cost calculator.
What fits in VRAM: 32 GB vs 80 GB
| Workload | RTX 5090 | A100 SXM4 |
|---|---|---|
| Largest LLM in FP16, one card | ~13B | ~32B |
| Largest LLM at 4-bit, one card | ~49B | ~123B |
| Flux dev (FP8, ~17 GB) | fits | fits |
| Wan 2.x 14B video (offloaded) | yes | yes |
| 70B 4-bit LLM on one card | no | yes |
Rules of thumb: ~2.4 GB per billion parameters in FP16 all-in, ~0.62 GB in 4-bit. Full tables in the VRAM guide.
Verdict: which should you rent?
The RTX 5090 beats the A100 SXM4 on raw FP16/FP4 throughput and bandwidth at a lower hourly rate; the A100 has 80 GB of HBM2e, NVLink and FP64. Under 32 GB the 5090 is the better rental; for multi-GPU training and 70B models, the A100.
- Cheaper per hour: RTX 5090 ($0.318 vs $0.583, −45%).
- More VRAM: A100 SXM4 (80 GB vs 32 GB).
- More FP16 throughput: RTX 5090 (about 1.3×).
- Best value per TFLOP-hour: RTX 5090.
- Best value per GB of VRAM: A100 SXM4.
- Multi-GPU: RTX 5090 over PCIe · A100 SXM4 with NVLink.
Related comparisons
RTX 5090 vs A100 SXM4: FAQ
Deeper reading: H100 vs H200 vs B200, RTX 4090 vs RTX 5090, how cloud GPU pricing works.
Is the RTX 5090 faster than the A100 SXM4?
On dense FP16 tensor throughput the RTX 5090 leads by about 1.3× (419 vs 312 TFLOPS). Memory bandwidth matters as much for inference: RTX 5090 1,792 GB/s vs A100 SXM4 2,039 GB/s.
Which is cheaper to rent, the RTX 5090 or the A100 SXM4?
The RTX 5090: $0.318/hr on-demand versus $0.583/hr — 45% less. Interruptible rates are $0.159 (RTX 5090) and $0.291 (A100 SXM4). Per TFLOP-hour the better value is the RTX 5090.
Which has more VRAM and what does that change?
The A100 SXM4 has 80 GB versus 32 GB. In LLM terms that is roughly a 32B FP16 model (or ~123B in 4-bit) on one card against 13B FP16 (~49B 4-bit). If the model does not fit, speed is irrelevant.
Can I rent both on PowerGPU right now?
Yes — 516 × RTX 5090 and 43 × A100 SXM4 are online as this page renders, deployable in about 30 seconds, billed per second, paid in crypto with no KYC.