Comparison · GPU vs GPU · read 00:32 UTCL4 vs A10G
Specifications, today's prices from 28 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.
| L4 | A10G | Difference | |
|---|---|---|---|
| Memory & compute | |||
| VRAM | 24 GB | 24 GB | 0% |
| Memory bandwidth | 0.30 TB/s | — | — |
| FP16 tensor | 121 TFLOPS | — | — |
| FP32 | 30.3 TFLOPS | — | — |
| Power | 72 W | — | — |
| Prices today | |||
| Cheapest on-demand | $0.27 | $1.00 | -73% |
| Median on-demand | $0.80 | $1.01 | -20% |
| Highest on-demand | $2.01 | $2.45 | -18% |
| Cheapest spot | $0.10 | $0.24 | -59% |
| Cheapest reserved | $0.32 | — | — |
| Current offers (n) | 72 | 11 | +555% |
| Providers with a fresh offer | 25 | 3 | +733% |
| Value | |||
| Per GB of VRAM · hour (cheapest) | $0.011 | $0.042 | -73% |
| Per GB of VRAM · hour (median) | $0.034 | $0.042 | -20% |
| Per PFLOP FP16 · hour (median) | $6.651 | — | — |
| Per TB/s · hour (median) | $2.683 | — | — |
| Trend | |||
| 30-day median change | -1.5% | — | — |
| 90-day median change | -2.8% | — | — |
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
Infomaniak2× $0.27 - 2
Hikube1× $0.27 - 3
OpenRelay1× $0.43
- 1
Hugging Face1× $1.00 - 2
AWSTrust 791× $1.01 - 3
BasetenTrust 871× $1.21
Verdict · computed from the numbers aboveChoose one, choose the other
Choose the L4 if…
- the hourly price matters most: median $0.80 against $1.01, 20% less.
- you want choice: 25 providers have a fresh offer today against 3.
Choose the A10G if…
- No metric above favours it today.
Questions about L4 vs A10G
Which is cheaper to rent, the L4 or the A10G?
Today the cheapest current on-demand L4 is $0.27 per GPU-hour and the cheapest A10G is $1.00; medians are $0.80 and $1.01. Cheapest excludes offers marked unavailable and counts one floor per marketplace.
How much memory do the L4 and A10G have?
24 GB of GDDR6 on the L4, 24 GB of memory on the A10G.
Where do these numbers come from?
From 83 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.