Comparison · GPU vs GPU · read 00:32 UTCCMP 170HX vs Tesla P4
Specifications, today's prices from 10 providers, price per unit of memory and compute, and who rents each cheapest. Better values are highlighted; lower is better for prices.
Side by sideSpecs, prices, value
Highlighted cells are the better of the two: more memory and compute, lower prices, lower cost per unit.
| CMP 170HX | Tesla P4 | Difference | |
|---|---|---|---|
| Memory & compute | |||
| VRAM | 8 GB | 8 GB | 0% |
| Memory bandwidth | 1.49 TB/s | 0.19 TB/s | +678% |
| FP16 tensor | — | — | — |
| FP32 | — | 5.5 TFLOPS | — |
| Power | 250 W | 75 W | +233% |
| Prices today | |||
| Cheapest on-demand | $0.24 | $0.04 | +508% |
| Median on-demand | $0.43 | $0.07 | +545% |
| Highest on-demand | $0.87 | $0.16 | +434% |
| Cheapest spot | $0.17 | $0.03 | +411% |
| Cheapest reserved | $0.47 | $0.13 | +260% |
| Current offers (n) | 12 | 4 | +200% |
| Providers with a fresh offer | 6 | 4 | +50% |
| Value | |||
| Per GB of VRAM · hour (cheapest) | $0.030 | $0.005 | +508% |
| Per GB of VRAM · hour (median) | $0.054 | $0.008 | +545% |
| Per PFLOP FP16 · hour (median) | — | — | — |
| Per TB/s · hour (median) | $0.291 | $0.351 | -17% |
| Trend | |||
| 30-day median change | +12.5% | 0.0% | — |
| 90-day median change | — | — | — |
90 days · median on-demand price · rebased to 100How the two have moved
Both medians indexed to 100 ninety days ago, so the slopes compare even though the price levels differ.
Cheapest providers today · on-demand · current offersWho rents each one cheapest
- 1
Vast.aiTrust 782× $0.24 - 2
Clore.aiTrust 469× $0.28 - 3
LiumTrust 402× $0.30
- 1Vast.aiTrust 781× $0.04
- 2
Akash NetworkTrust 531× $0.06
- 3
gcube1× $0.07
Verdict · computed from the numbers aboveChoose one, choose the other
Choose the CMP 170HX if…
- you serve LLMs: memory bandwidth per dollar is better ($0.291 per TB/s-hour against $0.351).
- you want choice: 6 providers have a fresh offer today against 4.
Choose the Tesla P4 if…
- the hourly price matters most: median $0.07 against $0.43, 85% less.
Questions about CMP 170HX vs Tesla P4
Which is cheaper to rent, the CMP 170HX or the Tesla P4?
Today the cheapest current on-demand CMP 170HX is $0.24 per GPU-hour and the cheapest Tesla P4 is $0.04; medians are $0.43 and $0.07. Cheapest excludes offers marked unavailable and counts one floor per marketplace.
How much memory do the CMP 170HX and Tesla P4 have?
8 GB of memory on the CMP 170HX, 8 GB of memory on the Tesla P4, at 1.49 and 0.19 TB/s.
Where do these numbers come from?
From 16 current offers read on the providers' own pages and APIs over the last 45 days (reference 00:32 UTC), or in our October 2026 market study for the few providers our collector does not read. Specifications come from manufacturer datasheets. Every price on the GPU pages links to its receipt and shows its read date.