Radeon RX 9070 GRE vs GeForce RTX 3090
Aggregate performance score
We've compared GeForce RTX 3090 and Radeon RX 9070 GRE, covering specs and all relevant benchmarks.
RTX 3090 outperforms 9070 GRE by a moderate 13% based on our aggregate benchmark results.
Contents
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 39 | 50 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 17.68 | 60.89 |
| Power efficiency | 14.08 | 19.86 |
| Architecture | Ampere (2020−2025) | RDNA 4.0 (2025−2026) |
| GPU code name | GA102 | Navi 48 |
| Market segment | Desktop | Desktop |
| Release date | 1 September 2020 (6 years ago) | 8 May 2025 (1 year ago) |
| Launch price (MSRP) | $1,499 | $549 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
RX 9070 GRE has 244% better value for money than RTX 3090.
Performance to price scatter graph
Currently popular graphics cards are shown for comparison.
Detailed specifications
General parameters such as number of shaders, GPU core base clock and boost clock speeds, manufacturing process, texturing and calculation speed. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 10496 | 3072 |
| Core clock speed | 1395 MHz | 1420 MHz |
| Boost clock speed | 1695 MHz | 2790 MHz |
| Number of transistors | 28,300 million | 53,900 million |
| Manufacturing process technology | 8 nm | 4 nm |
| Power consumption (TDP) | 350 Watt | 220 Watt |
| Texture fill rate | 556.0 | 535.7 |
| Floating-point processing power | 35.58 TFLOPS | 34.28 TFLOPS |
| ROPs | 112 | 96 |
| TMUs | 328 | 192 |
| Tensor Cores | 328 | 96 |
| Ray Tracing Cores | 82 | 48 |
| L0 Cache | no data | 768 KB |
| L1 Cache | 10.3 MB | no data |
| L2 Cache | 6 MB | 8 MB |
| L3 Cache | no data | 48 MB |
Form factor & compatibility
Information on compatibility with other computer components. Useful when choosing a future computer configuration or upgrading an existing one. For desktop graphics cards it's interface and bus (motherboard compatibility), additional power connectors (power supply compatibility).
| Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |
| Length | 336 mm | no data |
| Width | 3-slot | 2-slot |
| Supplementary power connectors | 1x 12-pin | 2x 8-pin |
VRAM capacity and type
Parameters of VRAM installed: its type, size, bus, clock and resulting bandwidth. Integrated GPUs have no dedicated video RAM and use a shared part of system RAM.
| Memory type | GDDR6X | GDDR6 |
| Maximum RAM amount | 24 GB | 12 GB |
| Memory bus width | 384 Bit | 192 Bit |
| Memory clock speed | 1219 MHz | 2250 MHz |
| Memory bandwidth | 936.2 GB/s | 432.0 GB/s |
| Shared memory | - | - |
| Resizable BAR | + | + |
Connectivity and outputs
This section shows the types and number of video connectors on each GPU. The data applies specifically to desktop reference models (for example, NVIDIA’s Founders Edition). OEM partners often modify both the number and types of ports. On notebook GPUs, video‐output options are determined by the laptop’s design rather than the graphics chip itself.
| Display Connectors | 1x HDMI, 3x DisplayPort | 1x HDMI 2.1b, 3x DisplayPort 2.1a |
| HDMI | + | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.5 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 2.2 |
| Vulkan | 1.2 | 1.4 |
| CUDA | 8.5 | - |
| DLSS | + | + |
Synthetic benchmarks
Non-gaming benchmark results comparison. The combined score is measured on a 0-100 point scale.
Combined synthetic benchmark score
This is our combined benchmark score.
Passmark
This is the most ubiquitous GPU benchmark. It gives the graphics card a thorough evaluation under various types of load, providing four separate benchmarks for Direct3D versions 9, 10, 11 and 12 (the last being done in 4K resolution if possible), and few more tests engaging DirectCompute capabilities.
3DMark Fire Strike Graphics
Fire Strike is a DirectX 11 benchmark for gaming PCs. It features two separate tests displaying a fight between a humanoid and a fiery creature made of lava. Using 1920x1080 resolution, Fire Strike shows off some realistic graphics and is quite taxing on hardware.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
Average FPS across all PC games
Here are the average frames per second in a large set of popular games across different resolutions:
| Full HD | 187
+16.9%
| 160 |
| 1440p | 120
+41.2%
| 85 |
| 4K | 81
+42.1%
| 57 |
Cost per frame, $
| 1080p | 8.02 | 3.43
+57.2%
|
| 1440p | 12.49 | 6.46
+48.3%
|
| 4K | 18.51 | 9.63
+48%
|
- RX 9070 GRE has 57% lower cost per frame in 1080p
- RX 9070 GRE has 48% lower cost per frame in 1440p
- RX 9070 GRE has 48% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Atomic Heart | 331
+87%
|
170−180 |
| Counter-Strike 2 | 349
+21.6%
|
280−290 |
| Cyberpunk 2077 | 209
+49.3%
|
140−150 |
| Resident Evil 4 Remake | 270
+60.7%
|
160−170 |
Full HD
Medium
| Atomic Heart | 262
+48%
|
170−180 |
| Battlefield 5 | 172
+5.5%
|
160−170 |
| Counter-Strike 2 | 347
+20.9%
|
280−290 |
| Cyberpunk 2077 | 178
+27.1%
|
140−150 |
| Far Cry 5 | 208
+20.2%
|
170−180 |
| Fortnite | 300−350
+18.4%
|
250−260 |
| Forza Horizon 4 | 254
+16%
|
210−220 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 350−400
+15.1%
|
300−350 |
Full HD
High
| Atomic Heart | 156 | 170−180
+13.5%
|
| Battlefield 5 | 158 | 160−170
+3.2%
|
| Counter-Strike 2 | 309
+7.7%
|
280−290 |
| Counter-Strike: Global Offensive | 270−280 | 270−280 |
| Cyberpunk 2077 | 154
+10%
|
140−150 |
| Dota 2 | 217
+14.2%
|
190−200 |
| Far Cry 5 | 196
+13.3%
|
170−180 |
| Fortnite | 300−350
+18.4%
|
250−260 |
| Forza Horizon 4 | 247
+12.8%
|
210−220 |
| Grand Theft Auto V | 171
+5.6%
|
160−170 |
| Metro Exodus | 176
+23.1%
|
140−150 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 369
+1.4%
|
364 |
| Valorant | 350−400
+15.1%
|
300−350 |
Full HD
Ultra
| Battlefield 5 | 146 | 160−170
+11.6%
|
| Cyberpunk 2077 | 136 | 140−150
+2.9%
|
| Dota 2 | 213
+18.3%
|
180−190 |
| Far Cry 5 | 183
+5.8%
|
170−180 |
| Forza Horizon 4 | 217 | 210−220
+0.9%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 182 | 197
+8.2%
|
| Valorant | 296
+13.8%
|
260−270 |
Full HD
Epic
| Fortnite | 300−350
+18.4%
|
250−260 |
1440p
High
| Counter-Strike 2 | 231
+40%
|
160−170 |
| Counter-Strike: Global Offensive | 450−500
+18%
|
400−450 |
| Grand Theft Auto V | 150
+22%
|
120−130 |
| Metro Exodus | 115
+26.4%
|
90−95 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+16.7%
|
150−160 |
| Valorant | 400−450
+18.6%
|
350−400 |
1440p
Ultra
| Battlefield 5 | 130 | 130−140
+6.9%
|
| Cyberpunk 2077 | 93
+20.8%
|
75−80 |
| Far Cry 5 | 171
+18.8%
|
140−150 |
| Forza Horizon 4 | 197
+8.2%
|
180−190 |
| The Witcher 3: Wild Hunt | 153
+7.7%
|
142 |
1440p
Epic
| Fortnite | 150−160 | 150−160 |
4K
High
| Atomic Heart | 55−60
+16%
|
50−55 |
| Counter-Strike 2 | 59 | 70−75
+25.4%
|
| Grand Theft Auto V | 182
+31.9%
|
130−140 |
| Metro Exodus | 76
+31%
|
55−60 |
| The Witcher 3: Wild Hunt | 154
+36.3%
|
113 |
| Valorant | 300−350
+1.3%
|
300−350 |
4K
Ultra
| Battlefield 5 | 113
+15.3%
|
95−100 |
| Counter-Strike 2 | 85−90
+16%
|
75−80 |
| Cyberpunk 2077 | 46
+27.8%
|
35−40 |
| Dota 2 | 202
+18.8%
|
170−180 |
| Far Cry 5 | 108
+24.1%
|
85−90 |
| Forza Horizon 4 | 153
+15.9%
|
130−140 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100 | 95−100 |
4K
Epic
| Fortnite | 75−80 | 75−80 |
This is how RTX 3090 and RX 9070 GRE compete in popular games:
- RTX 3090 is 17% faster in 1080p
- RTX 3090 is 41% faster in 1440p
- RTX 3090 is 42% faster in 4K
Here's the range of performance differences observed across popular games:
- in Atomic Heart, with 1080p resolution and the Low Preset, the RTX 3090 is 87% faster.
- in Counter-Strike 2, with 4K resolution and the High Preset, the RX 9070 GRE is 25% faster.
All in all, in popular games:
- RTX 3090 performs better in 40 tests (73%)
- RX 9070 GRE performs better in 8 tests (15%)
- there's a draw in 7 tests (13%)
Pros & cons summary
| Performance score | 63.28 | 56.10 |
| Recency | 1 September 2020 | 8 May 2025 |
| Maximum RAM amount | 24 GB | 12 GB |
| Chip lithography | 8 nm | 4 nm |
| Power consumption (TDP) | 350 Watt | 220 Watt |
RTX 3090 has a 13% higher aggregate performance score, and a 100% higher maximum VRAM amount.
RX 9070 GRE, on the other hand, has an age advantage of 4 years, a 50% more advanced lithography process, and 37% lower power consumption.
The GeForce RTX 3090 is our recommended choice as it beats the Radeon RX 9070 GRE in performance tests.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
