GPU comparison · 1080p benchmark
RX 9060 XT 8GB recorded 254 FPS against 212 FPS for RTX 3070 8GB. These are continuous 1080p benchmark averages, not predicted FPS in any particular game.
RTX 3070 8GB
212Benchmark FPS at 1080p- Our rating
- 63.3 / 100
- Graphics memory
- 8GB
- Released
- October 2020
- GPUsed cards tested
- 244
RX 9060 XT 8GB
254Benchmark FPS at 1080p- Our rating
- 67.4 / 100
- Graphics memory
- 8GB
- Released
- June 2025
- GPUsed cards tested
- 3
Change either GPU in the comparison tool
What does this comparison mean?
The RX 9060 XT 8GB leads the RTX 3070 in this workload while retaining the same capacity. This is the smaller-memory RDNA 4 version, so it does not offer the extra headroom of the 16GB model.
Both variants have 8GB 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
RTX 3070 8GB
The RTX 3070 is an 8GB GDDR6 Ampere model. NVIDIA set its retail availability for October 2020.
RX 9060 XT 8GB
The RX 9060 XT 8GB arrived in June 2025 with RDNA 4 architecture. Its 16GB sibling shares the model name but doubles the graphics-memory capacity.
Release and feature sources: RTX 3070 8GB source · RX 9060 XT 8GB 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.