P40 vs RTX 5090: Specs, VRAM & Price
Short answer: choose the RTX 5090 when 32 GB of VRAM is the gating requirement. Choose the P40 when 24 GB is enough for the workload and the lower hourly rate points that way.
The P40 has 24 GB of VRAM; the RTX 5090 has 32 GB.
You can rent both by the hour, no purchase required. P40 from $0.173/GPU/hr; RTX 5090 from $0.598/GPU/hr. The P40 is 71% cheaper at the entry rate.
P40
Good for inference workloads on older-generation hardware
RTX 5090
Good for inference and light fine-tuning workloads
Last updated: 2026-10-10 22:01:33 UTCRefreshes hourly
Specs side by side
| Spec | P40 | RTX 5090 |
|---|---|---|
| VRAM | 24 GB | 32 GB |
| Memory bandwidth | – | 1,792 GB/s |
| Architecture | Pascal | Blackwell |
| Compute capability | 6.1 | 12.0 |
| Precisions in hardware | FP32, FP16 | FP32, FP16, BF16, FP8, INT4 |
| Max board power (TDP) | – | 575W |
| Form factor | PCIe | PCIe 5.0 x16 |
| Regions | 1 | 4 |
On-demand price
| Rate | P40 | RTX 5090 |
|---|---|---|
| Lowest per GPU/hr | $0.173/GPU/hr (cheapest overall) | $1.09/GPU/hr |
Which is better for AI: P40 or RTX 5090?
Choose the RTX 5090 when 32 GB of VRAM is the gating requirement. Choose the P40 when 24 GB is enough for the workload and the lower hourly rate points that way.
P40 vs RTX 5090: common questions
Is the P40 or the RTX 5090 better for AI?
Short answer: choose the RTX 5090 when 32 GB of VRAM is the gating requirement. Choose the P40 when 24 GB is enough for the workload and the lower hourly rate points that way.
Is the P40 or the RTX 5090 cheaper to rent?
On Aquanode's live marketplace the P40 starts at $0.173/GPU/hr (median $0.173/GPU/hr) and the RTX 5090 starts at $0.598/GPU/hr (median $0.940/GPU/hr). The P40 is the cheaper of the two at the entry rate, by 71%.
What is the difference between the P40 and the RTX 5090?
The P40 has 24 GB of VRAM against the RTX 5090's 32 GB; the P40 is a Pascal part and the RTX 5090 is Blackwell (compute capability 6.1 vs 12.0); only the RTX 5090 supports BF16, FP8, INT4 compute. On price, the P40 lists from $0.173/GPU/hr and the RTX 5090 from $0.598/GPU/hr.
How widely available are the P40 and the RTX 5090?
The P40 is listed in 1 region and the RTX 5090 in 4 regions right now.
How much does 1,000 GPU-hours cost on the P40 vs the RTX 5090?
At the lowest rates listed today, 1,000 GPU-hours costs $173 on the P40 and $598 on the RTX 5090, a difference of $425 for the same runtime. Rates are per GPU per hour and update hourly.
How much VRAM does the P40 have compared to the RTX 5090?
The P40 has 24 GB of VRAM; the RTX 5090 has 32 GB.
How this comparison is calculated
Every price is normalized to a per-GPU hourly rate using the same pipeline as every other pricing surface on Aquanode, and only the cheapest qualifying offer per provider is shown. A dash means that provider does not currently list that GPU.
Architecture, compute capability and supported precisions come from each vendor's published datasheet for that generation, not from the marketplace feed. This page regenerates at most once per hour.
Memory bandwidth, tensor TFLOPS, NVLink/interconnect and max board power are the same verified-from-datasheet figures shown on each model's own P40 page and RTX 5090 page, which link the primary vendor source for that model. A dash here means Aquanode hasn't verified that figure from a primary source yet, never a guess.
Go further
Check what fits in each card's memory with the P40 VRAM calculator and the RTX 5090 VRAM calculator, or browse every model by generation in the GPU index.
More P40 comparisons
More RTX 5090 comparisons
Related reading: H100 pricing and specs, H100 vs H200, A100 vs H100, H100 and H200: SXM vs NVL vs PCIe, and The best GPUs for AI, ranked.
