GeForce RTX 3070 vs Radeon R9 390
Aggregate performance score
We've compared Radeon R9 390 and GeForce RTX 3070, covering specs and all relevant benchmarks.
RTX 3070 outperforms R9 390 by a whopping 152% 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 | 315 | 63 |
| Place by popularity | not in top-100 | 21 |
| Cost-effectiveness evaluation | 10.07 | 44.18 |
| Power efficiency | 5.92 | 18.67 |
| Architecture | GCN 2.0 (2013−2017) | Ampere (2020−2025) |
| GPU code name | Grenada | GA104 |
| Market segment | Desktop | Desktop |
| Design | reference | no data |
| Release date | 18 June 2015 (11 years ago) | 1 September 2020 (6 years ago) |
| Launch price (MSRP) | $329 | $499 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
RTX 3070 has 339% better value for money than R9 390.
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 | 2560 | 5888 |
| Core clock speed | no data | 1500 MHz |
| Boost clock speed | 1000 MHz | 1725 MHz |
| Number of transistors | 6,200 million | 17,400 million |
| Manufacturing process technology | 28 nm | 8 nm |
| Power consumption (TDP) | 275 Watt | 220 Watt |
| Texture fill rate | 160.0 | 317.4 |
| Floating-point processing power | 5.12 TFLOPS | 20.31 TFLOPS |
| ROPs | 64 | 96 |
| TMUs | 160 | 184 |
| Tensor Cores | no data | 184 |
| Ray Tracing Cores | no data | 46 |
| L1 Cache | 640 KB | 5.8 MB |
| L2 Cache | 1024 KB | 4 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).
| Bus support | PCIe 3.0 | no data |
| Interface | PCIe 3.0 x16 | PCIe 4.0 x16 |
| Length | 275 mm | 242 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1 x 6-pin, 1 x 8-pin | 1x 12-pin |
| Bridgeless CrossFire | + | - |
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 | GDDR5 | GDDR6 |
| High bandwidth memory (HBM) | - | no data |
| Maximum RAM amount | 0 MB | 8 GB |
| Memory bus width | 512 Bit | 256 Bit |
| Memory clock speed | 1000 MHz | 1750 MHz |
| Memory bandwidth | 384 GB/s | 448.0 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 | 2x DVI, 1x HDMI, 1x DisplayPort | 1x HDMI, 3x DisplayPort |
| Eyefinity | + | - |
| Number of Eyefinity displays | 6 | no data |
| HDMI | + | + |
| DisplayPort support | + | - |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| CrossFire | + | - |
| FreeSync | + | - |
| PowerTune | + | - |
| TrueAudio | + | - |
| VCE | + | - |
| DDMA audio | + | no data |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | DirectX® 12 | 12 Ultimate (12_2) |
| Shader Model | 6.3 | 6.5 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 2.0 |
| Vulkan | + | 1.2 |
| Mantle | + | - |
| 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 | 55−60
−63.1%
| 149 |
| 1440p | 35−40 | 99
+183%
|
| 4K | 24−27 | 63
+163%
|
Cost per frame, $
| 1080p | 5.98 | 3.35
+44%
|
| 1440p | 9.40 | 5.04
+46.4%
|
| 4K | 13.71 | 7.92
+42.2%
|
- RTX 3070 has 44% lower cost per frame in 1080p
- RTX 3070 has 46% lower cost per frame in 1440p
- RTX 3070 has 42% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Atomic Heart | 263 | 263 |
| Counter-Strike 2 | 270−280 | 270−280 |
| Cyberpunk 2077 | 147 | 147 |
Full HD
Medium
| Atomic Heart | 196 | 196 |
| Battlefield 5 | 149 | 149 |
| Counter-Strike 2 | 330 | 330 |
| Cyberpunk 2077 | 139 | 139 |
| Far Cry 5 | 154 | 154 |
| Fortnite | 230−240 | 230−240 |
| Forza Horizon 4 | 200−210 | 200−210 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 300−350 | 300−350 |
Full HD
High
| Atomic Heart | 113 | 113 |
| Battlefield 5 | 132 | 132 |
| Counter-Strike 2 | 257 | 257 |
| Counter-Strike: Global Offensive | 270−280 | 270−280 |
| Cyberpunk 2077 | 126 | 126 |
| Dota 2 | 133 | 133 |
| Far Cry 5 | 148 | 148 |
| Far Cry 6 | 110 | 110 |
| Fortnite | 230−240 | 230−240 |
| Forza Horizon 4 | 200−210 | 200−210 |
| Grand Theft Auto V | 139 | 139 |
| Metro Exodus | 120 | 120 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 230 | 230 |
| Valorant | 300−350 | 300−350 |
Full HD
Ultra
| Battlefield 5 | 119 | 119 |
| Cyberpunk 2077 | 102 | 102 |
| Dota 2 | 125 | 125 |
| Far Cry 5 | 141 | 141 |
| Forza Horizon 4 | 200−210 | 200−210 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 121 | 121 |
| Valorant | 237 | 237 |
Full HD
Epic
| Fortnite | 230−240 | 230−240 |
1440p
High
| Counter-Strike 2 | 167 | 167 |
| Counter-Strike: Global Offensive | 350−400 | 350−400 |
| Far Cry 6 | 91 | 91 |
| Grand Theft Auto V | 98 | 98 |
| Metro Exodus | 75 | 75 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 350−400 | 350−400 |
1440p
Ultra
| Battlefield 5 | 103 | 103 |
| Cyberpunk 2077 | 62 | 62 |
| Far Cry 5 | 125 | 125 |
| Forza Horizon 4 | 160−170 | 160−170 |
| The Witcher 3: Wild Hunt | 110−120 | 110−120 |
1440p
Epic
| Fortnite | 140−150 | 140−150 |
4K
High
| Atomic Heart | 45−50 | 45−50 |
| Counter-Strike 2 | 43 | 43 |
| Far Cry 6 | 42 | 42 |
| Grand Theft Auto V | 117 | 117 |
| Metro Exodus | 49 | 49 |
| The Witcher 3: Wild Hunt | 90 | 90 |
| Valorant | 300−350 | 300−350 |
4K
Ultra
| Battlefield 5 | 70 | 70 |
| Counter-Strike 2 | 65−70 | 65−70 |
| Cyberpunk 2077 | 30 | 30 |
| Dota 2 | 125 | 125 |
| Far Cry 5 | 70 | 70 |
| Forza Horizon 4 | 110−120 | 110−120 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 90−95 | 90−95 |
4K
Epic
| Fortnite | 75−80 | 75−80 |
This is how R9 390 and RTX 3070 compete in popular games:
- RTX 3070 is 171% faster in 1080p
- RTX 3070 is 183% faster in 1440p
- RTX 3070 is 163% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 20.90 | 52.74 |
| Recency | 18 June 2015 | 1 September 2020 |
| Chip lithography | 28 nm | 8 nm |
| Power consumption (TDP) | 275 Watt | 220 Watt |
RTX 3070 has a 152% higher aggregate performance score, an age advantage of 5 years, a 71% more advanced lithography process, and 20% lower power consumption.
The GeForce RTX 3070 is our recommended choice as it beats the Radeon R9 390 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.
