Component comparison
GeForce RTX 5060 vs GeForce RTX 4090
GeForce RTX 5060 vs GeForce RTX 4090 — detailed GPU comparison: performance, gaming FPS, specifications.
Advantages
A
GeForce RTX 5060
- + Release year (+2)
- + Die size (mm²) (+428 mm²)
- + Energy efficiency (+27.3)
B
GeForce RTX 4090
- + VRAM (GB) (+8 GB)
- + Memory clock (MHz) (+750 MHz)
- + Bandwidth (GB/s) (+586 GB/s)
- + Memory bus (bit) (+256 bit)
- + TGP / TDP (W) (+75 W)
- + Lithography (nm) (-1 nm)
- + Transistors (M) (+54,400M)
- + CUDA cores (+12544)
- + TMUs (+392)
- + ROPs (+128)
- + RT cores (+98)
- + Tensor cores (+392)
- + FP32 performance (TFLOPS) (+63.40 TFLOPS)
- + Pixel fill rate (GPixel/s) (+323.60 GPixel/s)
- + Texture fill rate (GTexel/s) (+990.40 GTexel/s)
- + PassMark (overall) (+10298)
- + 3DMark Fire Strike (+14825)
- + Normalized score (+24.7)
Detailed spec comparison
| Spec |
Component A
GeForce RTX 5060
|
Component B
GeForce RTX 4090
|
|---|---|---|
| Release year | 2025 (+2) | 2023 |
| VRAM (GB) | 8 GB | 16 GB (+8 GB) |
| Memory type | GDDR7 | GDDR6 |
| Memory clock (MHz) | 1500 MHz | 2250 MHz (+750 MHz) |
| Bandwidth (GB/s) | 448 GB/s | 1034 GB/s (+586 GB/s) |
| Memory bus (bit) | 128 bit | 384 bit (+256 bit) |
| TGP / TDP (W) | 45 W | 120 W (+75 W) |
| Lithography (nm) | 5 nm | 4 nm (-1 nm) |
| Transistors (M) | 21,900M | 76,300M (+54,400M) |
| Die size (mm²) | 181 mm² (+428 mm²) | 609 mm² |
| Base clock (MHz) | — | — |
| Boost clock (MHz) | — | — |
| CUDA cores | 3,840 | 16,384 (+12544) |
| TMUs | 120 | 512 (+392) |
| ROPs | 48 | 176 (+128) |
| RT cores | 30 | 128 (+98) |
| Tensor cores | 120 | 512 (+392) |
| FP32 performance (TFLOPS) | 19.18 TFLOPS | 82.58 TFLOPS (+63.40 TFLOPS) |
| Pixel fill rate (GPixel/s) | 119.90 GPixel/s | 443.50 GPixel/s (+323.60 GPixel/s) |
| Texture fill rate (GTexel/s) | 299.60 GTexel/s | 1290.00 GTexel/s (+990.40 GTexel/s) |
| Energy efficiency | 69.2 (+27.3) | 41.9 |
| PassMark (overall) | 16,749 | 27,047 (+10298) |
| 3DMark Time Spy | — | 21,251 |
| 3DMark Fire Strike | 31,366 | 46,191 (+14825) |
| Geekbench OpenCL | — | — |
| Geekbench Vulkan | — | — |
| Normalized score | 50.3 | 75.0 (+24.7) |
In both
CUDA
DLSS
ReBAR
ray_tracing
FPS in games (1080p)
| Game | GeForce RTX 5060 | GeForce RTX 4090 | Delta |
|---|---|---|---|
| Battlefield 5 | 130 FPS | 170 FPS | 30.8% (B) |
| CS:GO | 240 FPS | 240 FPS | ≈ |
| Counter-Strike 2 | 220 FPS | 300 FPS | 36.4% (B) |
| Cyberpunk 2077 | 95 FPS | 147 FPS | 54.7% (B) |
| Escape from Tarkov | 120 FPS | 120 FPS | ≈ |
| Far Cry 5 | 130 FPS | 173 FPS | 33.1% (B) |
| Fortnite | 170 FPS | 300 FPS | 76.5% (B) |
| Forza Horizon 4 | 150 FPS | 250 FPS | 66.7% (B) |
| Forza Horizon 5 | 255 FPS | 281 FPS | 10.2% (B) |
| GTA V | 140 FPS | 140 FPS | ≈ |
| Metro Exodus | 95 FPS | 156 FPS | 64.2% (B) |
| Overwatch | 240 FPS | 240 FPS | ≈ |
| PUBG | 140 FPS | 140 FPS | ≈ |
| Resident Evil 4 Remake | 110 FPS | 218 FPS | 98.2% (B) |
| The Witcher 3 | 140 FPS | 394 FPS | 181.4% (B) |
| Valorant | 230 FPS | 350 FPS | 52.2% (B) |
Specs from public sources (PassMark, Geekbench). FPS measured at 1080p medium settings.
Based on the comparison:
GeForce RTX 4090 wins 18 of the comparable criteria.
The choice depends on your use case.
🤔 How to choose
Universal advice for any use case.
- Reliability vs price: reliability (median 50) ↔ price (median 385.1).
- Weight vs CPU: mobility (median 48) ↔ overall performance (median 49.8).
- Upgradeability vs battery: upgradability (median 50) ↔ battery life (median 2.8).