Radeon Pro W6400 vs GeForce RTX 3070 Ti Mobile
Aggregate performance score
We've compared GeForce RTX 3070 Ti Mobile with Radeon Pro W6400, including specs and performance data.
RTX 3070 Ti Mobile outperforms Pro W6400 by a whopping 108% 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 | 103 | 309 |
| Place by popularity | not in top-100 | not in top-100 |
| Power efficiency | 28.04 | 31.02 |
| Architecture | Ampere (2020−2025) | RDNA 2.0 (2020−2025) |
| GPU code name | GA104 | Navi 24 |
| Market segment | Laptop | Workstation |
| Release date | 4 January 2022 (4 years ago) | 19 January 2022 (4 years ago) |
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 | 5632 | 768 |
| Core clock speed | 915 MHz | 2331 MHz |
| Boost clock speed | 1410 MHz | 2331 MHz |
| Number of transistors | 17,400 million | 5,400 million |
| Manufacturing process technology | 8 nm | 6 nm |
| Power consumption (TDP) | 115 Watt | 50 Watt |
| Texture fill rate | 248.2 | 111.9 |
| Floating-point processing power | 15.88 TFLOPS | 3.58 TFLOPS |
| ROPs | 80 | 32 |
| TMUs | 176 | 48 |
| Tensor Cores | 176 | no data |
| Ray Tracing Cores | 44 | 12 |
| L0 Cache | no data | 192 KB |
| L1 Cache | 5.5 MB | 256 KB |
| L2 Cache | 4 MB | 1024 KB |
| 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).
| Laptop size | large | no data |
| Interface | PCIe 4.0 x16 | PCIe 4.0 x4 |
| Width | no data | 1-slot |
| Supplementary power connectors | no data | 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 | GDDR6 | GDDR6 |
| Maximum RAM amount | 8 GB | 4 GB |
| Memory bus width | 256 Bit | 64 Bit |
| Memory clock speed | 1750 MHz | 1750 MHz |
| Memory bandwidth | 448.0 GB/s | 112.0 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 | No outputs | 2x DisplayPort 1.4a |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 Ultimate (12_2) | 12 Ultimate (12_2) |
| Shader Model | 6.6 | 6.6 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.2 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 8.6 | - |
| 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.
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 | 118
+115%
| 55−60
−115%
|
| 1440p | 72
+140%
| 30−35
−140%
|
| 4K | 48
+129%
| 21−24
−129%
|
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 230−240
+109%
|
110−120
−109%
|
| Cyberpunk 2077 | 129
+115%
|
60−65
−115%
|
| Resident Evil 4 Remake | 110−120
+111%
|
55−60
−111%
|
Full HD
Medium
| Battlefield 5 | 130−140
+114%
|
65−70
−114%
|
| Counter-Strike 2 | 230−240
+109%
|
110−120
−109%
|
| Cyberpunk 2077 | 111
+122%
|
50−55
−122%
|
| Far Cry 5 | 138
+112%
|
65−70
−112%
|
| Fortnite | 180−190
+113%
|
85−90
−113%
|
| Forza Horizon 4 | 160−170
+117%
|
75−80
−117%
|
| Forza Horizon 5 | 133
+122%
|
60−65
−122%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 160−170
+116%
|
75−80
−116%
|
| Valorant | 240−250
+119%
|
110−120
−119%
|
Full HD
High
| Battlefield 5 | 130−140
+114%
|
65−70
−114%
|
| Counter-Strike 2 | 230−240
+109%
|
110−120
−109%
|
| Counter-Strike: Global Offensive | 270−280
+115%
|
130−140
−115%
|
| Cyberpunk 2077 | 89
+123%
|
40−45
−123%
|
| Dota 2 | 146
+109%
|
70−75
−109%
|
| Far Cry 5 | 131
+118%
|
60−65
−118%
|
| Fortnite | 180−190
+113%
|
85−90
−113%
|
| Forza Horizon 4 | 160−170
+117%
|
75−80
−117%
|
| Forza Horizon 5 | 124
+125%
|
55−60
−125%
|
| Grand Theft Auto V | 141
+117%
|
65−70
−117%
|
| Metro Exodus | 95
+111%
|
45−50
−111%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 160−170
+116%
|
75−80
−116%
|
| The Witcher 3: Wild Hunt | 188
+109%
|
90−95
−109%
|
| Valorant | 240−250
+119%
|
110−120
−119%
|
Full HD
Ultra
| Battlefield 5 | 130−140
+114%
|
65−70
−114%
|
| Cyberpunk 2077 | 81
+131%
|
35−40
−131%
|
| Dota 2 | 138
+112%
|
65−70
−112%
|
| Far Cry 5 | 122
+122%
|
55−60
−122%
|
| Forza Horizon 4 | 160−170
+117%
|
75−80
−117%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 160−170
+116%
|
75−80
−116%
|
| The Witcher 3: Wild Hunt | 103
+129%
|
45−50
−129%
|
| Valorant | 193
+114%
|
90−95
−114%
|
Full HD
Epic
| Fortnite | 180−190
+113%
|
85−90
−113%
|
1440p
High
| Counter-Strike 2 | 110−120
+120%
|
50−55
−120%
|
| Counter-Strike: Global Offensive | 290−300
+113%
|
140−150
−113%
|
| Grand Theft Auto V | 94
+109%
|
45−50
−109%
|
| Metro Exodus | 53
+121%
|
24−27
−121%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180
+119%
|
80−85
−119%
|
| Valorant | 270−280
+108%
|
130−140
−108%
|
1440p
Ultra
| Battlefield 5 | 100−110
+112%
|
50−55
−112%
|
| Cyberpunk 2077 | 50
+108%
|
24−27
−108%
|
| Far Cry 5 | 100
+122%
|
45−50
−122%
|
| Forza Horizon 4 | 120−130
+124%
|
55−60
−124%
|
| The Witcher 3: Wild Hunt | 80−85
+137%
|
35−40
−137%
|
1440p
Epic
| Fortnite | 110−120
+128%
|
50−55
−128%
|
4K
High
| Counter-Strike 2 | 50−55
+108%
|
24−27
−108%
|
| Grand Theft Auto V | 95
+111%
|
45−50
−111%
|
| Metro Exodus | 35−40
+117%
|
18−20
−117%
|
| The Witcher 3: Wild Hunt | 76
+117%
|
35−40
−117%
|
| Valorant | 250−260
+114%
|
120−130
−114%
|
4K
Ultra
| Battlefield 5 | 65−70
+127%
|
30−33
−127%
|
| Counter-Strike 2 | 50−55
+108%
|
24−27
−108%
|
| Cyberpunk 2077 | 26
+117%
|
12−14
−117%
|
| Dota 2 | 128
+113%
|
60−65
−113%
|
| Far Cry 5 | 59
+119%
|
27−30
−119%
|
| Forza Horizon 4 | 80−85
+137%
|
35−40
−137%
|
| PLAYERUNKNOWN'S BATTLEGROUNDS | 60−65
+126%
|
27−30
−126%
|
4K
Epic
| Fortnite | 55−60
+111%
|
27−30
−111%
|
This is how RTX 3070 Ti Mobile and Pro W6400 compete in popular games:
- RTX 3070 Ti Mobile is 115% faster in 1080p
- RTX 3070 Ti Mobile is 140% faster in 1440p
- RTX 3070 Ti Mobile is 129% faster in 4K
Pros & cons summary
| Performance score | 41.88 | 20.14 |
| Maximum RAM amount | 8 GB | 4 GB |
| Chip lithography | 8 nm | 6 nm |
| Power consumption (TDP) | 115 Watt | 50 Watt |
RTX 3070 Ti Mobile has a 108% higher aggregate performance score, and a 100% higher maximum VRAM amount.
Pro W6400, on the other hand, has a 33% more advanced lithography process, and 130% lower power consumption.
The GeForce RTX 3070 Ti Mobile is our recommended choice as it beats the Radeon Pro W6400 in performance tests.
Be aware that GeForce RTX 3070 Ti Mobile is a notebook graphics card while Radeon Pro W6400 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.
