ATI Radeon HD 4350 vs GeForce RTX 3090
Aggregate performance score
We've compared GeForce RTX 3090 and Radeon HD 4350, covering specs and all relevant benchmarks.
RTX 3090 outperforms ATI HD 4350 by a whopping 17453% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 30 | 1274 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 14.97 | no data |
| Power efficiency | 13.53 | 1.35 |
| Architecture | Ampere (2020−2024) | TeraScale (2005−2013) |
| GPU code name | GA102 | RV710 |
| Market segment | Desktop | Desktop |
| Release date | 1 September 2020 (4 years ago) | 30 September 2008 (16 years ago) |
| Launch price (MSRP) | $1,499 | no data |
Cost-effectiveness evaluation
The higher the performance-to-price ratio, the better. We use the manufacturer's recommended prices 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. Note that power consumption of some graphics cards can well exceed their nominal TDP, especially when overclocked.
| Pipelines / CUDA cores | 10496 | 80 |
| Core clock speed | 1395 MHz | 600 MHz |
| Boost clock speed | 1695 MHz | no data |
| Number of transistors | 28,300 million | 242 million |
| Manufacturing process technology | 8 nm | 55 nm |
| Power consumption (TDP) | 350 Watt | 20 Watt |
| Texture fill rate | 556.0 | 4.800 |
| Floating-point processing power | 35.58 TFLOPS | 0.096 TFLOPS |
| ROPs | 112 | 4 |
| TMUs | 328 | 8 |
| Tensor Cores | 328 | no data |
| Ray Tracing Cores | 82 | no data |
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 2.0 x16 |
| Length | 336 mm | no data |
| Width | 3-slot | 1-slot |
| Supplementary power connectors | 1x 12-pin | None |
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 | DDR3 |
| Maximum RAM amount | 24 GB | 512 MB |
| Memory bus width | 384 Bit | 64 Bit |
| Memory clock speed | 1219 MHz | 400 MHz |
| Memory bandwidth | 936.2 GB/s | 6.4 GB/s |
| Shared memory | - | no data |
| Resizable BAR | + | - |
Connectivity and outputs
Types and number of video connectors present on the reviewed GPUs. As a rule, data in this section is precise only for desktop reference ones (so-called Founders Edition for NVIDIA chips). OEM manufacturers may change the number and type of output ports, while for notebook cards availability of certain video outputs ports depends on the laptop model rather than on the card itself.
| Display Connectors | 1x HDMI, 3x DisplayPort | 2x DisplayPort |
| HDMI | + | - |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 10.1 (10_1) |
| Shader Model | 6.5 | 4.1 |
| OpenGL | 4.6 | 3.3 |
| OpenCL | 2.0 | 1.1 |
| Vulkan | 1.2 | N/A |
| CUDA | 8.5 | - |
| DLSS | + | - |
Synthetic benchmark performance
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 Vantage Performance
3DMark Vantage is an outdated DirectX 10 benchmark using 1280x1024 screen resolution. It taxes the graphics card with two scenes, one depicting a girl escaping some militarized base located within a sea cave, the other displaying a space fleet attack on a defenseless planet. It was discontinued in April 2017, and Time Spy benchmark is now recommended to be used instead.
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 | 193
+2657%
| 7
−2657%
|
| 1440p | 127 | 0−1 |
| 4K | 85 | -0−1 |
Cost per frame, $
| 1080p | 7.77 | no data |
| 1440p | 11.80 | no data |
| 4K | 17.64 | no data |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 331
+16450%
|
2−3
−16450%
|
| Counter-Strike 2 | 349
+34800%
|
1−2
−34800%
|
| Cyberpunk 2077 | 209
+20800%
|
1−2
−20800%
|
Full HD
Medium Preset
| Atomic Heart | 262
+13000%
|
2−3
−13000%
|
| Battlefield 5 | 172 | 0−1 |
| Counter-Strike 2 | 347
+34600%
|
1−2
−34600%
|
| Cyberpunk 2077 | 178
+17700%
|
1−2
−17700%
|
| Far Cry 5 | 208
+20700%
|
1−2
−20700%
|
| Fortnite | 300−350
+30100%
|
1−2
−30100%
|
| Forza Horizon 4 | 254
+8367%
|
3−4
−8367%
|
| Forza Horizon 5 | 210
+20900%
|
1−2
−20900%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+2429%
|
7−8
−2429%
|
| Valorant | 350−400
+1237%
|
27−30
−1237%
|
Full HD
High Preset
| Atomic Heart | 156
+7700%
|
2−3
−7700%
|
| Battlefield 5 | 158 | 0−1 |
| Counter-Strike 2 | 309
+30800%
|
1−2
−30800%
|
| Counter-Strike: Global Offensive | 270−280
+1886%
|
14−16
−1886%
|
| Cyberpunk 2077 | 154
+15300%
|
1−2
−15300%
|
| Dota 2 | 217
+2070%
|
10−11
−2070%
|
| Far Cry 5 | 196
+19500%
|
1−2
−19500%
|
| Fortnite | 300−350
+30100%
|
1−2
−30100%
|
| Forza Horizon 4 | 247
+8133%
|
3−4
−8133%
|
| Forza Horizon 5 | 195
+19400%
|
1−2
−19400%
|
| Grand Theft Auto V | 171 | 0−1 |
| Metro Exodus | 176
+17500%
|
1−2
−17500%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+2429%
|
7−8
−2429%
|
| The Witcher 3: Wild Hunt | 369
+9125%
|
4−5
−9125%
|
| Valorant | 350−400
+1237%
|
27−30
−1237%
|
Full HD
Ultra Preset
| Battlefield 5 | 146 | 0−1 |
| Cyberpunk 2077 | 136
+13500%
|
1−2
−13500%
|
| Dota 2 | 213
+2030%
|
10−11
−2030%
|
| Far Cry 5 | 183
+18200%
|
1−2
−18200%
|
| Forza Horizon 4 | 217
+7133%
|
3−4
−7133%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+2429%
|
7−8
−2429%
|
| The Witcher 3: Wild Hunt | 182
+4450%
|
4−5
−4450%
|
| Valorant | 296
+996%
|
27−30
−996%
|
Full HD
Epic Preset
| Fortnite | 300−350
+30100%
|
1−2
−30100%
|
1440p
High Preset
| Counter-Strike 2 | 231
+23000%
|
1−2
−23000%
|
| Counter-Strike: Global Offensive | 450−500 | 0−1 |
| Grand Theft Auto V | 150 | 0−1 |
| Metro Exodus | 115 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+4275%
|
4−5
−4275%
|
| Valorant | 400−450
+21800%
|
2−3
−21800%
|
1440p
Ultra Preset
| Battlefield 5 | 130 | 0−1 |
| Cyberpunk 2077 | 93 | 0−1 |
| Far Cry 5 | 171 | 0−1 |
| Forza Horizon 4 | 197
+19600%
|
1−2
−19600%
|
| The Witcher 3: Wild Hunt | 153 | 0−1 |
1440p
Epic Preset
| Fortnite | 150−160 | 0−1 |
4K
High Preset
| Atomic Heart | 55−60 | 0−1 |
| Counter-Strike 2 | 59 | 0−1 |
| Grand Theft Auto V | 182
+1113%
|
14−16
−1113%
|
| Metro Exodus | 76 | 0−1 |
| The Witcher 3: Wild Hunt | 154 | 0−1 |
| Valorant | 300−350
+16450%
|
2−3
−16450%
|
4K
Ultra Preset
| Battlefield 5 | 113 | 0−1 |
| Counter-Strike 2 | 85−90 | 0−1 |
| Cyberpunk 2077 | 46 | 0−1 |
| Dota 2 | 202
+20100%
|
1−2
−20100%
|
| Far Cry 5 | 108
+10700%
|
1−2
−10700%
|
| Forza Horizon 4 | 153 | 0−1 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+4700%
|
2−3
−4700%
|
4K
Epic Preset
| Fortnite | 75−80
+3850%
|
2−3
−3850%
|
This is how RTX 3090 and ATI HD 4350 compete in popular games:
- RTX 3090 is 2657% faster in 1080p
Here's the range of performance differences observed across popular games:
- in Cyberpunk 2077, with 1080p resolution and the Low Preset, the RTX 3090 is 20800% faster.
All in all, in popular games:
- Without exception, RTX 3090 surpassed ATI HD 4350 in all 28 of our tests.
Pros & cons summary
| Performance score | 59.68 | 0.34 |
| Recency | 1 September 2020 | 30 September 2008 |
| Maximum RAM amount | 24 GB | 512 MB |
| Chip lithography | 8 nm | 55 nm |
| Power consumption (TDP) | 350 Watt | 20 Watt |
RTX 3090 has a 17452.9% higher aggregate performance score, an age advantage of 11 years, a 4700% higher maximum VRAM amount, and a 587.5% more advanced lithography process.
ATI HD 4350, on the other hand, has 1650% lower power consumption.
The GeForce RTX 3090 is our recommended choice as it beats the Radeon HD 4350 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.
