GPU comparison · 1080p benchmark
RX 7800 XT 16GB recorded 305 FPS against 105 FPS for GTX 1070 8GB. These are continuous 1080p benchmark averages, not predicted FPS in any particular game.
GTX 1070 8GB
105Benchmark FPS at 1080p- Our rating
- 49.5 / 100
- Graphics memory
- 8GB
- Released
- June 2016
- GPUsed cards tested
- 131
RX 7800 XT 16GB
305Benchmark FPS at 1080p- Our rating
- 71.9 / 100
- Graphics memory
- 16GB
- Released
- September 2023
- GPUsed cards tested
- 27
Change either GPU in the comparison tool
What does this comparison mean?
The RX 7800 XT 16GB doubles the GTX 1070's 8GB and records a much higher average. The Pascal-to-RDNA 3 change needs a software and system check, particularly when the existing GTX 1070 is installed in an older build.
GTX 1070 8GB has 8GB and RX 7800 XT 16GB has 16GB of graphics memory. Memory capacity, board dimensions, power connectors and the price of a particular used card are separate from this benchmark. Compare the exact item before deciding whether to upgrade.
The two GPUs in context
GTX 1070 8GB
The GTX 1070 is a Pascal model with 8GB of GDDR5, launched in June 2016.
RX 7800 XT 16GB
The RX 7800 XT combines RDNA 3 with 16GB of GDDR6. It became available in September 2023 alongside the 12GB RX 7700 XT.
Release and feature sources: GTX 1070 8GB source · RX 7800 XT 16GB source.
How the figures are compared
Both FPS figures come from the owner-supplied GPUsed benchmark dataset. GPUsed reports a continuous FurMark run at 1080p for its physical-card checks. The percentage compares the higher model average with the lower one using the original FPS values. Our rating uses a compressed scale, with the fastest GPU at 100; it is separate from the percentage difference. A benchmark result does not predict gaming FPS.
GPUsed reports its physical-card checks typically last 30 to 60 minutes while temperature and stability are checked. The owner supplied the model-level FPS workbook on 2 October 2026; this benchmark dataset was last reconciled 3 October 2026. Historical cards tested are separate from the number of FPS runs behind a model average. Full benchmark method.