Tesla K80 vs GeForce RTX 3080
Aggregate performance score
We've compared GeForce RTX 3080 with Tesla K80, including specs and performance data.
RTX 3080 outperforms Tesla K80 by a whopping 330% based on our aggregate benchmark results.
Primary details
GPU architecture, market segment, value for money and other general parameters compared.
| Place in the ranking | 31 | 360 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 46.43 | no data |
| Power efficiency | 14.04 | 3.48 |
| Architecture | Ampere (2020−2024) | Kepler 2.0 (2013−2015) |
| GPU code name | GA102 | GK210 |
| Market segment | Desktop | Workstation |
| Release date | 1 September 2020 (4 years ago) | 17 November 2014 (10 years ago) |
| Launch price (MSRP) | $699 | 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 | 8704 | 2496 ×2 |
| Core clock speed | 1440 MHz | 562 MHz |
| Boost clock speed | 1710 MHz | 824 MHz |
| Number of transistors | 28,300 million | 7,100 million |
| Manufacturing process technology | 8 nm | 28 nm |
| Power consumption (TDP) | 320 Watt | 300 Watt |
| Texture fill rate | 465.1 | 171.4 ×2 |
| Floating-point processing power | 29.77 TFLOPS | 4.113 TFLOPS ×2 |
| ROPs | 96 | 48 ×2 |
| TMUs | 272 | 208 ×2 |
| Tensor Cores | 272 | no data |
| Ray Tracing Cores | 68 | 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 3.0 x16 |
| Length | 285 mm | 267 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 1x 12-pin | 1x 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 | GDDR5 |
| Maximum RAM amount | 10 GB | 12 GB ×2 |
| Memory bus width | 320 Bit | 384 Bit ×2 |
| Memory clock speed | 1188 MHz | 1253 MHz |
| Memory bandwidth | 760.3 GB/s | 240.6 GB/s ×2 |
| 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 | 1x HDMI, 3x DisplayPort | No outputs |
| HDMI | + | - |
API and SDK compatibility
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 (11_1) |
| Shader Model | 6.5 | 5.1 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 2.0 | 1.2 |
| Vulkan | 1.2 | 1.1.126 |
| CUDA | 8.5 | 3.7 |
| 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 CUDA
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 CUDA API by NVIDIA.
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 | 167
+377%
| 35−40
−377%
|
| 1440p | 126
+367%
| 27−30
−367%
|
| 4K | 88
+389%
| 18−21
−389%
|
Cost per frame, $
| 1080p | 4.19 | no data |
| 1440p | 5.55 | no data |
| 4K | 7.94 | no data |
FPS performance in popular games
Full HD
Low Preset
| Atomic Heart | 307
+339%
|
70−75
−339%
|
| Counter-Strike 2 | 150−160
+340%
|
35−40
−340%
|
| Cyberpunk 2077 | 150−160
+331%
|
35−40
−331%
|
Full HD
Medium Preset
| Atomic Heart | 239
+335%
|
55−60
−335%
|
| Battlefield 5 | 172
+391%
|
35−40
−391%
|
| Counter-Strike 2 | 150−160
+340%
|
35−40
−340%
|
| Cyberpunk 2077 | 138
+360%
|
30−33
−360%
|
| Far Cry 5 | 157
+349%
|
35−40
−349%
|
| Fortnite | 280−290
+340%
|
65−70
−340%
|
| Forza Horizon 4 | 230−240
+372%
|
50−55
−372%
|
| Forza Horizon 5 | 152
+334%
|
35−40
−334%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+343%
|
40−45
−343%
|
| Valorant | 300−350
+347%
|
75−80
−347%
|
Full HD
High Preset
| Atomic Heart | 147
+390%
|
30−33
−390%
|
| Battlefield 5 | 156
+346%
|
35−40
−346%
|
| Counter-Strike 2 | 150−160
+340%
|
35−40
−340%
|
| Counter-Strike: Global Offensive | 270−280
+363%
|
60−65
−363%
|
| Cyberpunk 2077 | 134
+347%
|
30−33
−347%
|
| Dota 2 | 147
+390%
|
30−33
−390%
|
| Far Cry 5 | 150
+400%
|
30−33
−400%
|
| Fortnite | 280−290
+340%
|
65−70
−340%
|
| Forza Horizon 4 | 230−240
+372%
|
50−55
−372%
|
| Forza Horizon 5 | 140
+367%
|
30−33
−367%
|
| Grand Theft Auto V | 147
+390%
|
30−33
−390%
|
| Metro Exodus | 128
+374%
|
27−30
−374%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+343%
|
40−45
−343%
|
| The Witcher 3: Wild Hunt | 303
+333%
|
70−75
−333%
|
| Valorant | 300−350
+347%
|
75−80
−347%
|
Full HD
Ultra Preset
| Battlefield 5 | 145
+383%
|
30−33
−383%
|
| Counter-Strike 2 | 150−160
+340%
|
35−40
−340%
|
| Cyberpunk 2077 | 131
+337%
|
30−33
−337%
|
| Dota 2 | 135
+350%
|
30−33
−350%
|
| Far Cry 5 | 140
+367%
|
30−33
−367%
|
| Forza Horizon 4 | 230−240
+372%
|
50−55
−372%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+343%
|
40−45
−343%
|
| The Witcher 3: Wild Hunt | 149
+397%
|
30−33
−397%
|
| Valorant | 268
+347%
|
60−65
−347%
|
Full HD
Epic Preset
| Fortnite | 280−290
+340%
|
65−70
−340%
|
1440p
High Preset
| Counter-Strike 2 | 55−60
+358%
|
12−14
−358%
|
| Counter-Strike: Global Offensive | 450−500
+351%
|
100−105
−351%
|
| Grand Theft Auto V | 112
+367%
|
24−27
−367%
|
| Metro Exodus | 95
+352%
|
21−24
−352%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+338%
|
40−45
−338%
|
| Valorant | 350−400
+337%
|
90−95
−337%
|
1440p
Ultra Preset
| Battlefield 5 | 124
+359%
|
27−30
−359%
|
| Cyberpunk 2077 | 86
+378%
|
18−20
−378%
|
| Far Cry 5 | 135
+350%
|
30−33
−350%
|
| Forza Horizon 4 | 200−210
+344%
|
45−50
−344%
|
| The Witcher 3: Wild Hunt | 130−140
+360%
|
30−33
−360%
|
1440p
Epic Preset
| Fortnite | 150−160
+331%
|
35−40
−331%
|
4K
High Preset
| Atomic Heart | 50−55
+350%
|
12−14
−350%
|
| Counter-Strike 2 | 35−40
+333%
|
9−10
−333%
|
| Grand Theft Auto V | 143
+377%
|
30−33
−377%
|
| Metro Exodus | 65
+364%
|
14−16
−364%
|
| The Witcher 3: Wild Hunt | 115
+379%
|
24−27
−379%
|
| Valorant | 300−350
+335%
|
75−80
−335%
|
4K
Ultra Preset
| Battlefield 5 | 91
+333%
|
21−24
−333%
|
| Counter-Strike 2 | 35−40
+333%
|
9−10
−333%
|
| Cyberpunk 2077 | 43
+378%
|
9−10
−378%
|
| Dota 2 | 129
+378%
|
27−30
−378%
|
| Far Cry 5 | 94
+348%
|
21−24
−348%
|
| Forza Horizon 4 | 150−160
+400%
|
30−33
−400%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100
+357%
|
21−24
−357%
|
4K
Epic Preset
| Fortnite | 75−80
+339%
|
18−20
−339%
|
This is how RTX 3080 and Tesla K80 compete in popular games:
- RTX 3080 is 377% faster in 1080p
- RTX 3080 is 367% faster in 1440p
- RTX 3080 is 389% faster in 4K
Pros & cons summary
| Performance score | 64.71 | 15.04 |
| Recency | 1 September 2020 | 17 November 2014 |
| Maximum RAM amount | 10 GB | 12 GB |
| Chip lithography | 8 nm | 28 nm |
| Power consumption (TDP) | 320 Watt | 300 Watt |
RTX 3080 has a 330.3% higher aggregate performance score, an age advantage of 5 years, and a 250% more advanced lithography process.
Tesla K80, on the other hand, has a 20% higher maximum VRAM amount, and 6.7% lower power consumption.
The GeForce RTX 3080 is our recommended choice as it beats the Tesla K80 in performance tests.
Be aware that GeForce RTX 3080 is a desktop card while Tesla K80 is a workstation one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
