GeForce RTX 3090 vs P104-100
Aggregate performance score
We've compared P104-100 with GeForce RTX 3090, including specs and performance data.
RTX 3090 outperforms P104-100 by a whopping 636% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 478 | 27 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | no data | 14.96 |
| Power efficiency | no data | 13.67 |
| Architecture | Pascal (2016−2021) | Ampere (2020−2024) |
| GPU code name | GP104 | GA102 |
| Market segment | Workstation | Desktop |
| Release date | 12 December 2017 (7 years ago) | 1 September 2020 (4 years ago) |
| Launch price (MSRP) | no data | $1,499 |
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 | 1920 | 10496 |
| Core clock speed | 1607 MHz | 1395 MHz |
| Boost clock speed | 1733 MHz | 1695 MHz |
| Number of transistors | 7,200 million | 28,300 million |
| Manufacturing process technology | 16 nm | 8 nm |
| Power consumption (TDP) | no data | 350 Watt |
| Texture fill rate | 208.0 | 556.0 |
| Floating-point processing power | 6.655 TFLOPS | 35.58 TFLOPS |
| ROPs | 64 | 112 |
| TMUs | 120 | 328 |
| Tensor Cores | no data | 328 |
| Ray Tracing Cores | no data | 82 |
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 3.0 x16 | PCIe 4.0 x16 |
| Length | 267 mm | 336 mm |
| Width | 2-slot | 3-slot |
| Supplementary power connectors | 1x 8-pin | 1x 12-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 | GDDR5X | GDDR6X |
| Maximum RAM amount | 4 GB | 24 GB |
| Memory bus width | 256 Bit | 384 Bit |
| Memory clock speed | 1251 MHz | 1219 MHz |
| Memory bandwidth | 320.3 GB/s | 936.2 GB/s |
| Shared memory | - | - |
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 | No outputs | 1x HDMI, 3x DisplayPort |
| HDMI | - | + |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| Shader Model | 6.4 | 6.5 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 2.0 |
| Vulkan | 1.2.131 | 1.2 |
| CUDA | 6.1 | 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.
GeekBench 5 OpenCL
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses OpenCL API by Khronos Group.
GeekBench 5 Vulkan
Geekbench 5 is a widespread graphics card benchmark combined from 11 different test scenarios. All these scenarios rely on direct usage of GPU's processing power, no 3D rendering is involved. This variation uses Vulkan API by AMD & Khronos Group.
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 | 24−27
−725%
| 198
+725%
|
| 1440p | 16−18
−700%
| 128
+700%
|
| 4K | 10−12
−770%
| 87
+770%
|
Cost per frame, $
| 1080p | no data | 7.57 |
| 1440p | no data | 11.71 |
| 4K | no data | 17.23 |
FPS performance in popular games
Full HD
Low Preset
| Counter-Strike 2 | 220
+0%
|
220
+0%
|
| Cyberpunk 2077 | 207
+0%
|
207
+0%
|
Full HD
Medium Preset
| Battlefield 5 | 102
+0%
|
102
+0%
|
| Counter-Strike 2 | 188
+0%
|
188
+0%
|
| Cyberpunk 2077 | 151
+0%
|
151
+0%
|
| Forza Horizon 4 | 505
+0%
|
505
+0%
|
| Forza Horizon 5 | 184
+0%
|
184
+0%
|
| Metro Exodus | 169
+0%
|
169
+0%
|
| Red Dead Redemption 2 | 130
+0%
|
130
+0%
|
| Valorant | 393
+0%
|
393
+0%
|
Full HD
High Preset
| Battlefield 5 | 110−120
+0%
|
110−120
+0%
|
| Counter-Strike 2 | 161
+0%
|
161
+0%
|
| Cyberpunk 2077 | 135
+0%
|
135
+0%
|
| Dota 2 | 186
+0%
|
186
+0%
|
| Far Cry 5 | 147
+0%
|
147
+0%
|
| Fortnite | 270−280
+0%
|
270−280
+0%
|
| Forza Horizon 4 | 402
+0%
|
402
+0%
|
| Forza Horizon 5 | 182
+0%
|
182
+0%
|
| Grand Theft Auto V | 171
+0%
|
171
+0%
|
| Metro Exodus | 150
+0%
|
150
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+0%
|
210−220
+0%
|
| Red Dead Redemption 2 | 132
+0%
|
132
+0%
|
| The Witcher 3: Wild Hunt | 170−180
+0%
|
170−180
+0%
|
| Valorant | 222
+0%
|
222
+0%
|
| World of Tanks | 270−280
+0%
|
270−280
+0%
|
Full HD
Ultra Preset
| Battlefield 5 | 95
+0%
|
95
+0%
|
| Counter-Strike 2 | 146
+0%
|
146
+0%
|
| Cyberpunk 2077 | 121
+0%
|
121
+0%
|
| Dota 2 | 213
+0%
|
213
+0%
|
| Far Cry 5 | 130−140
+0%
|
130−140
+0%
|
| Forza Horizon 4 | 351
+0%
|
351
+0%
|
| Forza Horizon 5 | 159
+0%
|
159
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 210−220
+0%
|
210−220
+0%
|
| Valorant | 296
+0%
|
296
+0%
|
1440p
High Preset
| Counter-Strike 2 | 35−40
+0%
|
35−40
+0%
|
| Dota 2 | 150
+0%
|
150
+0%
|
| Grand Theft Auto V | 150
+0%
|
150
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+0%
|
170−180
+0%
|
| Red Dead Redemption 2 | 92
+0%
|
92
+0%
|
| World of Tanks | 450−500
+0%
|
450−500
+0%
|
1440p
Ultra Preset
| Battlefield 5 | 91
+0%
|
91
+0%
|
| Cyberpunk 2077 | 87
+0%
|
87
+0%
|
| Far Cry 5 | 160−170
+0%
|
160−170
+0%
|
| Forza Horizon 4 | 266
+0%
|
266
+0%
|
| Forza Horizon 5 | 134
+0%
|
134
+0%
|
| Metro Exodus | 139
+0%
|
139
+0%
|
| The Witcher 3: Wild Hunt | 152
+0%
|
152
+0%
|
| Valorant | 295
+0%
|
295
+0%
|
4K
High Preset
| Counter-Strike 2 | 40−45
+0%
|
40−45
+0%
|
| Dota 2 | 182
+0%
|
182
+0%
|
| Grand Theft Auto V | 182
+0%
|
182
+0%
|
| Metro Exodus | 76
+0%
|
76
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 200−210
+0%
|
200−210
+0%
|
| Red Dead Redemption 2 | 64
+0%
|
64
+0%
|
| The Witcher 3: Wild Hunt | 182
+0%
|
182
+0%
|
4K
Ultra Preset
| Battlefield 5 | 91
+0%
|
91
+0%
|
| Counter-Strike 2 | 22
+0%
|
22
+0%
|
| Cyberpunk 2077 | 45
+0%
|
45
+0%
|
| Dota 2 | 202
+0%
|
202
+0%
|
| Far Cry 5 | 100−110
+0%
|
100−110
+0%
|
| Fortnite | 95−100
+0%
|
95−100
+0%
|
| Forza Horizon 4 | 159
+0%
|
159
+0%
|
| Forza Horizon 5 | 83
+0%
|
83
+0%
|
| Valorant | 188
+0%
|
188
+0%
|
This is how P104-100 and RTX 3090 compete in popular games:
- RTX 3090 is 725% faster in 1080p
- RTX 3090 is 700% faster in 1440p
- RTX 3090 is 770% faster in 4K
All in all, in popular games:
- there's a draw in 64 tests (100%)
Pros & cons summary
| Performance score | 9.06 | 66.64 |
| Recency | 12 December 2017 | 1 September 2020 |
| Maximum RAM amount | 4 GB | 24 GB |
| Chip lithography | 16 nm | 8 nm |
RTX 3090 has a 635.5% higher aggregate performance score, an age advantage of 2 years, a 500% higher maximum VRAM amount, and a 100% more advanced lithography process.
The GeForce RTX 3090 is our recommended choice as it beats the P104-100 in performance tests.
Be aware that P104-100 is a workstation graphics card while GeForce RTX 3090 is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
