Component comparison
GeForce RTX 5070 vs GeForce GTX 1660 Ti
GeForce RTX 5070 vs GeForce GTX 1660 Ti — detailed GPU comparison: performance, gaming FPS, specifications.
Advantages
A
GeForce RTX 5070
- + Release year (+6)
- + VRAM (GB) (+2 GB)
- + Memory clock (MHz) (+500 MHz)
- + Bandwidth (GB/s) (+384 GB/s)
- + TGP / TDP (W) (+20 W)
- + Lithography (nm) (-8 nm)
- + Transistors (M) (+24,500M)
- + Die size (mm²) (+21 mm²)
- + CUDA cores (+4608)
- + TMUs (+96)
- + ROPs (+32)
- + FP32 performance (TFLOPS) (+26.77 TFLOPS)
- + Pixel fill rate (GPixel/s) (+116.04 GPixel/s)
- + Texture fill rate (GTexel/s) (+312.40 GTexel/s)
- + PassMark (overall) (+6457)
- + 3DMark Fire Strike (+20131)
- + Normalized score (+5.9)
B
GeForce GTX 1660 Ti
- + Energy efficiency (+3.6)
Detailed spec comparison
| Spec |
Component A
GeForce RTX 5070
|
Component B
GeForce GTX 1660 Ti
|
|---|---|---|
| Release year | 2025 (+6) | 2019 |
| VRAM (GB) | 8 GB (+2 GB) | 6 GB |
| Memory type | GDDR7 | GDDR6 |
| Memory clock (MHz) | 2000 MHz (+500 MHz) | 1500 MHz |
| Bandwidth (GB/s) | 672 GB/s (+384 GB/s) | 288 GB/s |
| Memory bus (bit) | 192 bit | 192 bit |
| TGP / TDP (W) | 100 W (+20 W) | 80 W |
| Lithography (nm) | 4 nm (-8 nm) | 12 nm |
| Transistors (M) | 31,100M (+24,500M) | 6,600M |
| Die size (mm²) | 263 mm² (+21 mm²) | 284 mm² |
| Base clock (MHz) | — | — |
| Boost clock (MHz) | — | — |
| CUDA cores | 6,144 (+4608) | 1,536 |
| TMUs | 192 (+96) | 96 |
| ROPs | 80 (+32) | 48 |
| RT cores | 48 | — |
| Tensor cores | 192 | — |
| FP32 performance (TFLOPS) | 30.87 TFLOPS (+26.77 TFLOPS) | 4.10 TFLOPS |
| Pixel fill rate (GPixel/s) | 201.00 GPixel/s (+116.04 GPixel/s) | 84.96 GPixel/s |
| Texture fill rate (GTexel/s) | 482.30 GTexel/s (+312.40 GTexel/s) | 169.90 GTexel/s |
| Energy efficiency | 21.3 | 24.9 (+3.6) |
| PassMark (overall) | 19,075 (+6457) | 12,618 |
| 3DMark Time Spy | — | 5,659 |
| 3DMark Fire Strike | 34,949 (+20131) | 14,818 |
| Geekbench OpenCL | — | 60,911 |
| Geekbench Vulkan | — | 58,130 |
| Normalized score | 69.6 (+5.9) | 63.7 |
Only in component A
DLSS
ReBAR
ray_tracing
In both
CUDA
FPS in games (1080p)
| Game | GeForce RTX 5070 | GeForce GTX 1660 Ti | Delta |
|---|---|---|---|
| Battlefield 5 | 180 FPS | 111 FPS | +62.2% (A) |
| CS:GO | 240 FPS | 240 FPS | ≈ |
| Counter-Strike 2 | 300 FPS | 147 FPS | +104.1% (A) |
| Cyberpunk 2077 | 170 FPS | 86 FPS | +97.7% (A) |
| Far Cry 5 | 322 FPS | 93 FPS | +246.2% (A) |
| Fortnite | 300 FPS | 120 FPS | +150% (A) |
| Forza Horizon 4 | 270 FPS | 134 FPS | +101.5% (A) |
| Forza Horizon 5 | 329 FPS | 107 FPS | +207.5% (A) |
| GTA V | 140 FPS | 140 FPS | ≈ |
| Metro Exodus | 170 FPS | 54 FPS | +214.8% (A) |
| Overwatch | 240 FPS | 240 FPS | ≈ |
| PUBG | 140 FPS | 140 FPS | ≈ |
| Resident Evil 4 Remake | 210 FPS | 75 FPS | +180% (A) |
| The Witcher 3 | 436 FPS | 103 FPS | +323.3% (A) |
| Valorant | 400 FPS | 209 FPS | +91.4% (A) |
Specs from public sources (PassMark, Geekbench). FPS measured at 1080p medium settings.
Based on the comparison:
GeForce RTX 5070 wins 17 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).