Tesla T4 vs Radeon HD 6970
Aggregate performance score
We've compared Radeon HD 6970 with Tesla T4, including specs and performance data.
T4 outperforms HD 6970 by a whopping 258% 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 | 596 | 260 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 0.93 | no data |
| Power efficiency | 2.08 | 26.62 |
| Architecture | TeraScale 3 (2010−2013) | Turing (2018−2022) |
| GPU code name | Cayman | TU104 |
| Market segment | Desktop | Workstation |
| Design | reference | no data |
| Release date | 14 December 2010 (14 years ago) | 13 September 2018 (7 years ago) |
| Launch price (MSRP) | $369 | 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 | 1536 | 2560 |
| Core clock speed | no data | 585 MHz |
| Boost clock speed | 880 MHz | 1590 MHz |
| Number of transistors | 2,640 million | 13,600 million |
| Manufacturing process technology | 40 nm | 12 nm |
| Power consumption (TDP) | 550 Watt | 70 Watt |
| Texture fill rate | 84.48 | 254.4 |
| Floating-point processing power | 2.703 TFLOPS | 8.141 TFLOPS |
| ROPs | 32 | 64 |
| TMUs | 96 | 160 |
| Tensor Cores | no data | 320 |
| Ray Tracing Cores | no data | 40 |
| L1 Cache | 192 KB | 2.5 MB |
| L2 Cache | 512 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 2.0 x16 | no data |
| Interface | PCIe 2.0 x16 | PCIe 3.0 x16 |
| Length | 286 mm | 168 mm |
| Width | 2-slot | 1-slot |
| 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 | GDDR6 |
| Maximum RAM amount | 2 GB | 16 GB |
| Memory bus width | 256 Bit | 256 Bit |
| Memory clock speed | 1375 MHz | 1250 MHz |
| Memory bandwidth | no data | 320.0 GB/s |
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 1.4a, 2x mini-DisplayPort 1.2 | No outputs |
| Eyefinity | + | - |
| HDMI | + | - |
Supported technologies
Supported technological solutions. This information will prove useful if you need some particular technology for your purposes.
| CrossFire | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | DirectX® 11 | 12 Ultimate (12_1) |
| Shader Model | 5.0 | 6.5 |
| OpenGL | 4.4 | 4.6 |
| OpenCL | 1.2 | 1.2 |
| Vulkan | - | 1.2.131 |
| CUDA | - | 7.5 |
| 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.
Gaming performance
Let's see how good the compared graphics cards are for gaming. Particular gaming benchmark results are measured in FPS.
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 35−40
−243%
|
120−130
+243%
|
| Cyberpunk 2077 | 14−16
−257%
|
50−55
+257%
|
Full HD
Medium
| Battlefield 5 | 30−33
−233%
|
100−105
+233%
|
| Counter-Strike 2 | 35−40
−243%
|
120−130
+243%
|
| Cyberpunk 2077 | 14−16
−257%
|
50−55
+257%
|
| Escape from Tarkov | 27−30
−252%
|
95−100
+252%
|
| Far Cry 5 | 21−24
−241%
|
75−80
+241%
|
| Fortnite | 40−45
−257%
|
150−160
+257%
|
| Forza Horizon 4 | 30−35
−255%
|
110−120
+255%
|
| Forza Horizon 5 | 20−22
−250%
|
70−75
+250%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
−240%
|
85−90
+240%
|
| Valorant | 75−80
−247%
|
260−270
+247%
|
Full HD
High
| Battlefield 5 | 30−33
−233%
|
100−105
+233%
|
| Counter-Strike 2 | 35−40
−243%
|
120−130
+243%
|
| Counter-Strike: Global Offensive | 110−120
−215%
|
350−400
+215%
|
| Cyberpunk 2077 | 14−16
−257%
|
50−55
+257%
|
| Dota 2 | 50−55
−252%
|
190−200
+252%
|
| Escape from Tarkov | 27−30
−252%
|
95−100
+252%
|
| Far Cry 5 | 21−24
−241%
|
75−80
+241%
|
| Fortnite | 40−45
−257%
|
150−160
+257%
|
| Forza Horizon 4 | 30−35
−255%
|
110−120
+255%
|
| Forza Horizon 5 | 20−22
−250%
|
70−75
+250%
|
| Grand Theft Auto V | 24−27
−240%
|
85−90
+240%
|
| Metro Exodus | 12−14
−246%
|
45−50
+246%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
−240%
|
85−90
+240%
|
| The Witcher 3: Wild Hunt | 18−20
−233%
|
60−65
+233%
|
| Valorant | 75−80
−247%
|
260−270
+247%
|
Full HD
Ultra
| Battlefield 5 | 30−33
−233%
|
100−105
+233%
|
| Cyberpunk 2077 | 14−16
−257%
|
50−55
+257%
|
| Dota 2 | 50−55
−252%
|
190−200
+252%
|
| Escape from Tarkov | 27−30
−252%
|
95−100
+252%
|
| Far Cry 5 | 21−24
−241%
|
75−80
+241%
|
| Forza Horizon 4 | 30−35
−255%
|
110−120
+255%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 24−27
−240%
|
85−90
+240%
|
| The Witcher 3: Wild Hunt | 18−20
−233%
|
60−65
+233%
|
| Valorant | 75−80
−247%
|
260−270
+247%
|
Full HD
Epic
| Fortnite | 40−45
−257%
|
150−160
+257%
|
1440p
High
| Counter-Strike 2 | 12−14
−246%
|
45−50
+246%
|
| Counter-Strike: Global Offensive | 50−55
−240%
|
180−190
+240%
|
| Grand Theft Auto V | 8−9
−238%
|
27−30
+238%
|
| Metro Exodus | 7−8
−243%
|
24−27
+243%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45
−250%
|
140−150
+250%
|
| Valorant | 75−80
−251%
|
270−280
+251%
|
1440p
Ultra
| Battlefield 5 | 12−14
−246%
|
45−50
+246%
|
| Cyberpunk 2077 | 5−6
−220%
|
16−18
+220%
|
| Escape from Tarkov | 12−14
−246%
|
45−50
+246%
|
| Far Cry 5 | 14−16
−257%
|
50−55
+257%
|
| Forza Horizon 4 | 16−18
−244%
|
55−60
+244%
|
| The Witcher 3: Wild Hunt | 9−10
−233%
|
30−33
+233%
|
1440p
Epic
| Fortnite | 14−16
−257%
|
50−55
+257%
|
4K
High
| Counter-Strike 2 | 0−1 | 0−1 |
| Grand Theft Auto V | 18−20
−233%
|
60−65
+233%
|
| Metro Exodus | 2−3
−250%
|
7−8
+250%
|
| The Witcher 3: Wild Hunt | 5−6
−220%
|
16−18
+220%
|
| Valorant | 35−40
−243%
|
120−130
+243%
|
4K
Ultra
| Battlefield 5 | 6−7
−250%
|
21−24
+250%
|
| Counter-Strike 2 | 0−1 | 0−1 |
| Cyberpunk 2077 | 2−3
−250%
|
7−8
+250%
|
| Dota 2 | 24−27
−240%
|
85−90
+240%
|
| Escape from Tarkov | 5−6
−220%
|
16−18
+220%
|
| Far Cry 5 | 6−7
−250%
|
21−24
+250%
|
| Forza Horizon 4 | 10−12
−218%
|
35−40
+218%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 7−8
−243%
|
24−27
+243%
|
4K
Epic
| Fortnite | 7−8
−243%
|
24−27
+243%
|
Pros & cons summary
| Performance score | 6.74 | 24.16 |
| Recency | 14 December 2010 | 13 September 2018 |
| Maximum RAM amount | 2 GB | 16 GB |
| Chip lithography | 40 nm | 12 nm |
| Power consumption (TDP) | 550 Watt | 70 Watt |
Tesla T4 has a 258.5% higher aggregate performance score, an age advantage of 7 years, a 700% higher maximum VRAM amount, a 233.3% more advanced lithography process, and 685.7% lower power consumption.
The Tesla T4 is our recommended choice as it beats the Radeon HD 6970 in performance tests.
Be aware that Radeon HD 6970 is a desktop graphics card while Tesla T4 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.
