Radeon Pro W6800 vs HD 7870
Aggregate performance score
We've compared Radeon HD 7870 with Radeon Pro W6800, including specs and performance data.
Pro W6800 outperforms HD 7870 by a whopping 341% 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 | 466 | 77 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 2.56 | 10.65 |
| Power efficiency | 4.80 | 14.85 |
| Architecture | GCN 1.0 (2012−2020) | RDNA 2.0 (2020−2025) |
| GPU code name | Pitcairn | Navi 21 |
| Market segment | Desktop | Workstation |
| Release date | 5 March 2012 (13 years ago) | 8 June 2021 (4 years ago) |
| Launch price (MSRP) | $349 | $2,249 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Pro W6800 has 316% better value for money than HD 7870.
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 | 1280 | 3840 |
| Core clock speed | 1000 MHz | 2075 MHz |
| Boost clock speed | no data | 2320 MHz |
| Number of transistors | 2,800 million | 26,800 million |
| Manufacturing process technology | 28 nm | 7 nm |
| Power consumption (TDP) | 175 Watt | 250 Watt |
| Texture fill rate | 80.00 | 556.8 |
| Floating-point processing power | 2.56 TFLOPS | 17.82 TFLOPS |
| ROPs | 32 | 96 |
| TMUs | 80 | 240 |
| Ray Tracing Cores | no data | 60 |
| L0 Cache | no data | 960 KB |
| L1 Cache | 320 KB | 768 KB |
| L2 Cache | 512 KB | 4 MB |
| L3 Cache | no data | 128 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 3.0 x16 | PCIe 4.0 x16 |
| Length | 241 mm | 267 mm |
| Width | 2-slot | 2-slot |
| Supplementary power connectors | 2x 6-pin | 1x 6-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 | GDDR5 | GDDR6 |
| Maximum RAM amount | 2 GB | 32 GB |
| Memory bus width | 256 Bit | 256 Bit |
| Memory clock speed | 1200 MHz | 2000 MHz |
| Memory bandwidth | 153.6 GB/s | 512.0 GB/s |
| Shared memory | - | - |
| Resizable BAR | - | + |
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 | 1x DVI, 1x HDMI, 2x mini-DisplayPort | 6x mini-DisplayPort |
| Eyefinity | + | - |
| HDMI | + | - |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (11_1) | 12 Ultimate (12_2) |
| Shader Model | 5.1 | 6.5 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 2.1 |
| Vulkan | 1.2.131 | 1.2 |
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.
3DMark 11 Performance GPU
3DMark 11 is an obsolete DirectX 11 benchmark by Futuremark. It used four tests based on two scenes, one being few submarines exploring the submerged wreck of a sunken ship, the other is an abandoned temple deep in the jungle. All the tests are heavy with volumetric lighting and tessellation, and despite being done in 1280x720 resolution, are relatively taxing. Discontinued in January 2020, 3DMark 11 is now superseded by Time Spy.
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:
| 900p | 84
−317%
| 350−400
+317%
|
| Full HD | 66
−108%
| 137
+108%
|
| 1440p | 24−27
−383%
| 116
+383%
|
| 4K | 18−20
−367%
| 84
+367%
|
Cost per frame, $
| 1080p | 5.29
+210%
| 16.42
−210%
|
| 1440p | 14.54
+33.3%
| 19.39
−33.3%
|
| 4K | 19.39
+38.1%
| 26.77
−38.1%
|
- HD 7870 has 210% lower cost per frame in 1080p
- HD 7870 has 33% lower cost per frame in 1440p
- HD 7870 has 38% lower cost per frame in 4K
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 60−65
−328%
|
250−260
+328%
|
| Cyberpunk 2077 | 21−24
−409%
|
110−120
+409%
|
| Hogwarts Legacy | 20−22
−495%
|
110−120
+495%
|
Full HD
Medium
| Battlefield 5 | 45−50
−206%
|
150−160
+206%
|
| Counter-Strike 2 | 60−65
−328%
|
250−260
+328%
|
| Cyberpunk 2077 | 21−24
−409%
|
110−120
+409%
|
| Far Cry 5 | 35−40
−94.4%
|
70
+94.4%
|
| Fortnite | 65−70
−218%
|
210−220
+218%
|
| Forza Horizon 4 | 45−50
−298%
|
180−190
+298%
|
| Forza Horizon 5 | 30−35
−344%
|
150−160
+344%
|
| Hogwarts Legacy | 20−22
−495%
|
110−120
+495%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45
−330%
|
170−180
+330%
|
| Valorant | 100−110
−166%
|
260−270
+166%
|
Full HD
High
| Battlefield 5 | 45−50
−206%
|
150−160
+206%
|
| Counter-Strike 2 | 60−65
−328%
|
250−260
+328%
|
| Counter-Strike: Global Offensive | 160−170
−72.2%
|
270−280
+72.2%
|
| Cyberpunk 2077 | 21−24
−409%
|
110−120
+409%
|
| Dota 2 | 75−80
−28.6%
|
99
+28.6%
|
| Far Cry 5 | 35−40
−80.6%
|
65
+80.6%
|
| Fortnite | 65−70
−218%
|
210−220
+218%
|
| Forza Horizon 4 | 45−50
−298%
|
180−190
+298%
|
| Forza Horizon 5 | 30−35
−344%
|
150−160
+344%
|
| Grand Theft Auto V | 40−45
−188%
|
121
+188%
|
| Hogwarts Legacy | 20−22
−495%
|
110−120
+495%
|
| Metro Exodus | 21−24
−627%
|
160
+627%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45
−330%
|
170−180
+330%
|
| The Witcher 3: Wild Hunt | 36
−453%
|
199
+453%
|
| Valorant | 100−110
−166%
|
260−270
+166%
|
Full HD
Ultra
| Battlefield 5 | 45−50
−206%
|
150−160
+206%
|
| Cyberpunk 2077 | 21−24
−409%
|
110−120
+409%
|
| Dota 2 | 75−80
−11.7%
|
86
+11.7%
|
| Far Cry 5 | 35−40
−72.2%
|
62
+72.2%
|
| Forza Horizon 4 | 45−50
−298%
|
180−190
+298%
|
| Hogwarts Legacy | 20−22
−495%
|
110−120
+495%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 40−45
−330%
|
170−180
+330%
|
| The Witcher 3: Wild Hunt | 20
−685%
|
157
+685%
|
| Valorant | 100−110
−166%
|
260−270
+166%
|
Full HD
Epic
| Fortnite | 65−70
−218%
|
210−220
+218%
|
1440p
High
| Counter-Strike 2 | 21−24
−538%
|
130−140
+538%
|
| Counter-Strike: Global Offensive | 80−85
−315%
|
300−350
+315%
|
| Grand Theft Auto V | 16−18
−450%
|
88
+450%
|
| Metro Exodus | 12−14
−1215%
|
171
+1215%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 65−70
−157%
|
170−180
+157%
|
| Valorant | 120−130
−152%
|
300−350
+152%
|
1440p
Ultra
| Battlefield 5 | 27−30
−314%
|
120−130
+314%
|
| Cyberpunk 2077 | 9−10
−589%
|
60−65
+589%
|
| Far Cry 5 | 24−27
−167%
|
64
+167%
|
| Forza Horizon 4 | 27−30
−448%
|
140−150
+448%
|
| Hogwarts Legacy | 12−14
−400%
|
60−65
+400%
|
| The Witcher 3: Wild Hunt | 16−18
−531%
|
100−110
+531%
|
1440p
Epic
| Fortnite | 24−27
−458%
|
130−140
+458%
|
4K
High
| Counter-Strike 2 | 6−7
−900%
|
60−65
+900%
|
| Grand Theft Auto V | 21−24
−468%
|
125
+468%
|
| Hogwarts Legacy | 6−7
−433%
|
30−35
+433%
|
| Metro Exodus | 7−8
−686%
|
55
+686%
|
| The Witcher 3: Wild Hunt | 14−16
−607%
|
99
+607%
|
| Valorant | 55−60
−388%
|
280−290
+388%
|
4K
Ultra
| Battlefield 5 | 14−16
−433%
|
80−85
+433%
|
| Counter-Strike 2 | 6−7
−900%
|
60−65
+900%
|
| Cyberpunk 2077 | 4−5
−625%
|
27−30
+625%
|
| Dota 2 | 40−45
−129%
|
94
+129%
|
| Far Cry 5 | 10−12
−445%
|
60
+445%
|
| Forza Horizon 4 | 18−20
−437%
|
100−110
+437%
|
| Hogwarts Legacy | 6−7
−433%
|
30−35
+433%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 10−12
−609%
|
75−80
+609%
|
4K
Epic
| Fortnite | 10−12
−536%
|
70−75
+536%
|
This is how HD 7870 and Pro W6800 compete in popular games:
- Pro W6800 is 317% faster in 900p
- Pro W6800 is 108% faster in 1080p
- Pro W6800 is 383% faster in 1440p
- Pro W6800 is 367% faster in 4K
Here's the range of performance differences observed across popular games:
- in Metro Exodus, with 1440p resolution and the High Preset, the Pro W6800 is 1215% faster.
All in all, in popular games:
- Without exception, Pro W6800 surpassed HD 7870 in all 66 of our tests.
Pros & cons summary
| Performance score | 10.92 | 48.20 |
| Recency | 5 March 2012 | 8 June 2021 |
| Maximum RAM amount | 2 GB | 32 GB |
| Chip lithography | 28 nm | 7 nm |
| Power consumption (TDP) | 175 Watt | 250 Watt |
HD 7870 has 42.9% lower power consumption.
Pro W6800, on the other hand, has a 341.4% higher aggregate performance score, an age advantage of 9 years, a 1500% higher maximum VRAM amount, and a 300% more advanced lithography process.
The Radeon Pro W6800 is our recommended choice as it beats the Radeon HD 7870 in performance tests.
Be aware that Radeon HD 7870 is a desktop graphics card while Radeon Pro W6800 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.
