Radeon 660M vs Tesla K20c
Aggregate performance score
We've compared Tesla K20c with Radeon 660M, including specs and performance data.
K20c outperforms 660M by a small 7% 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 | 556 | 572 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 0.16 | no data |
| Power efficiency | 2.82 | 14.82 |
| Architecture | Kepler (2012−2018) | RDNA 2.0 (2020−2025) |
| GPU code name | GK110 | Rembrandt+ |
| Market segment | Workstation | Laptop |
| Release date | 12 November 2012 (13 years ago) | 3 January 2023 (3 years ago) |
| Launch price (MSRP) | $3,199 | no data |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
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 | 2496 | 384 |
| Core clock speed | 706 MHz | 1500 MHz |
| Boost clock speed | no data | 1900 MHz |
| Number of transistors | 7,080 million | 13,100 million |
| Manufacturing process technology | 28 nm | 6 nm |
| Power consumption (TDP) | 225 Watt | 40 Watt |
| Texture fill rate | 146.8 | 45.60 |
| Floating-point processing power | 3.524 TFLOPS | 1.459 TFLOPS |
| ROPs | 40 | 16 |
| TMUs | 208 | 24 |
| Ray Tracing Cores | no data | 6 |
| L0 Cache | no data | 96 KB |
| L1 Cache | 208 KB | 128 KB |
| L2 Cache | 1280 KB | 2 MB |
| L3 Cache | no data | 8 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 2.0 x16 | PCIe 4.0 x8 |
| Length | 267 mm | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 1x 6-pin + 1x 8-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 | GDDR5 | System Shared |
| Maximum RAM amount | 5 GB | System Shared |
| Memory bus width | 320 Bit | System Shared |
| Memory clock speed | 1300 MHz | System Shared |
| Memory bandwidth | 208.0 GB/s | no data |
| Shared memory | - | + |
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 | No outputs | Portable Device Dependent |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_0) | 12 Ultimate (12_2) |
| Shader Model | 5.1 | 6.7 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 2.0 |
| Vulkan | 1.1.126 | 1.3 |
| CUDA | 3.5 | - |
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
+4.3%
| 23
−4.3%
|
| 4K | 12−14
−8.3%
| 13
+8.3%
|
Cost per frame, $
| 1080p | 133.29 | no data |
| 4K | 266.58 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 78
+0%
|
78
+0%
|
| Cyberpunk 2077 | 24
+0%
|
24
+0%
|
| Resident Evil 4 Remake | 20
+0%
|
20
+0%
|
Full HD
Medium
| Battlefield 5 | 30−35
+0%
|
30−35
+0%
|
| Counter-Strike 2 | 57
+0%
|
57
+0%
|
| Cyberpunk 2077 | 20
+0%
|
20
+0%
|
| Far Cry 5 | 30
+0%
|
30
+0%
|
| Fortnite | 45−50
+0%
|
45−50
+0%
|
| Forza Horizon 4 | 35−40
+0%
|
35−40
+0%
|
| Forza Horizon 5 | 39
+0%
|
39
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
+0%
|
27−30
+0%
|
| Valorant | 80−85
+0%
|
80−85
+0%
|
Full HD
High
| Battlefield 5 | 30−35
+0%
|
30−35
+0%
|
| Counter-Strike 2 | 23
+0%
|
23
+0%
|
| Counter-Strike: Global Offensive | 120−130
+0%
|
120−130
+0%
|
| Cyberpunk 2077 | 14
+0%
|
14
+0%
|
| Dota 2 | 56
+0%
|
56
+0%
|
| Far Cry 5 | 26
+0%
|
26
+0%
|
| Fortnite | 45−50
+0%
|
45−50
+0%
|
| Forza Horizon 4 | 35−40
+0%
|
35−40
+0%
|
| Forza Horizon 5 | 32
+0%
|
32
+0%
|
| Grand Theft Auto V | 25
+0%
|
25
+0%
|
| Metro Exodus | 15
+0%
|
15
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
+0%
|
27−30
+0%
|
| The Witcher 3: Wild Hunt | 26
+0%
|
26
+0%
|
| Valorant | 80−85
+0%
|
80−85
+0%
|
Full HD
Ultra
| Battlefield 5 | 30−35
+0%
|
30−35
+0%
|
| Cyberpunk 2077 | 16−18
+0%
|
16−18
+0%
|
| Dota 2 | 48
+0%
|
48
+0%
|
| Far Cry 5 | 25
+0%
|
25
+0%
|
| Forza Horizon 4 | 35−40
+0%
|
35−40
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 27−30
+0%
|
27−30
+0%
|
| The Witcher 3: Wild Hunt | 15
+0%
|
15
+0%
|
| Valorant | 80−85
+0%
|
80−85
+0%
|
Full HD
Epic
| Fortnite | 45−50
+0%
|
45−50
+0%
|
1440p
High
| Counter-Strike 2 | 14−16
+0%
|
14−16
+0%
|
| Counter-Strike: Global Offensive | 60−65
+0%
|
60−65
+0%
|
| Grand Theft Auto V | 9−10
+0%
|
9−10
+0%
|
| Metro Exodus | 8−9
+0%
|
8−9
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45
+0%
|
40−45
+0%
|
| Valorant | 85−90
+0%
|
85−90
+0%
|
1440p
Ultra
| Battlefield 5 | 16−18
+0%
|
16−18
+0%
|
| Cyberpunk 2077 | 6−7
+0%
|
6−7
+0%
|
| Far Cry 5 | 16−18
+0%
|
16−18
+0%
|
| Forza Horizon 4 | 18−20
+0%
|
18−20
+0%
|
| The Witcher 3: Wild Hunt | 10−12
+0%
|
10−12
+0%
|
1440p
Epic
| Fortnite | 16−18
+0%
|
16−18
+0%
|
4K
High
| Counter-Strike 2 | 2−3
+0%
|
2−3
+0%
|
| Grand Theft Auto V | 18−20
+0%
|
18−20
+0%
|
| Metro Exodus | 3−4
+0%
|
3−4
+0%
|
| The Witcher 3: Wild Hunt | 7−8
+0%
|
7−8
+0%
|
| Valorant | 40−45
+0%
|
40−45
+0%
|
4K
Ultra
| Battlefield 5 | 8−9
+0%
|
8−9
+0%
|
| Counter-Strike 2 | 2−3
+0%
|
2−3
+0%
|
| Cyberpunk 2077 | 2−3
+0%
|
2−3
+0%
|
| Dota 2 | 27−30
+0%
|
27−30
+0%
|
| Far Cry 5 | 7−8
+0%
|
7−8
+0%
|
| Forza Horizon 4 | 12−14
+0%
|
12−14
+0%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8
+0%
|
7−8
+0%
|
4K
Epic
| Fortnite | 7−8
+0%
|
7−8
+0%
|
This is how Tesla K20c and Radeon 660M compete in popular games:
- Tesla K20c is 4% faster in 1080p
- Radeon 660M is 8% faster in 4K
All in all, in popular games:
- there's a draw in 60 tests (100%)
Pros & cons summary
| Performance score | 8.24 | 7.70 |
| Recency | 12 November 2012 | 3 January 2023 |
| Chip lithography | 28 nm | 6 nm |
| Power consumption (TDP) | 225 Watt | 40 Watt |
Tesla K20c has a 7% higher aggregate performance score.
Radeon 660M, on the other hand, has an age advantage of 10 years, a 367% more advanced lithography process, and 463% lower power consumption.
Given the minimal performance differences, no clear winner can be declared between Tesla K20c and Radeon 660M.
Be aware that Tesla K20c is a workstation graphics card while Radeon 660M is a notebook one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
