Radeon RX 9070 vs Tesla P4
Aggregate performance score
We've compared Tesla P4 with Radeon RX 9070, including specs and performance data.
RX 9070 outperforms P4 by a whopping 179% 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 | 300 | 42 |
| Place by popularity | not in top-100 | 95 |
| Cost-effectiveness evaluation | no data | 65.86 |
| Power efficiency | 22.60 | 21.47 |
| Architecture | Pascal (2016−2021) | RDNA 4.0 (2025−2026) |
| GPU code name | GP104 | Navi 48 |
| Market segment | Workstation | Desktop |
| Release date | 13 September 2016 (10 years ago) | 6 March 2025 (1 year ago) |
| Launch price (MSRP) | no data | $549 |
Cost-effectiveness evaluation
The higher the ratio, the better. We use the manufacturer's recommended prices.
Performance to price scatter graph
Currently popular graphics cards are shown 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. Real power consumption of some graphics cards can well exceed their nominal TDP, especially if overclocked.
| Pipelines / CUDA cores | 2560 | 3584 |
| Core clock speed | 886 MHz | 1330 MHz |
| Boost clock speed | 1114 MHz | 2520 MHz |
| Number of transistors | 7,200 million | 53,900 million |
| Manufacturing process technology | 16 nm | 5 nm |
| Power consumption (TDP) | 75 Watt | 220 Watt |
| Texture fill rate | 178.2 | 564.5 |
| Floating-point processing power | 5.704 TFLOPS | 36.13 TFLOPS |
| ROPs | 64 | 128 |
| TMUs | 160 | 224 |
| Tensor Cores | no data | 112 |
| Ray Tracing Cores | no data | 56 |
| L0 Cache | no data | 896 KB |
| L1 Cache | 960 KB | no data |
| L2 Cache | 2 MB | 8 MB |
| L3 Cache | no data | 64 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 5.0 x16 |
| Length | 168 mm | 267 mm |
| Width | 1-slot | 2-slot |
| Supplementary power connectors | None | 2x 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 | 8 GB | 16 GB |
| Memory bus width | 256 Bit | 256 Bit |
| Memory clock speed | 1502 MHz | 2518 MHz |
| Memory bandwidth | 192.3 GB/s | 644.6 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 | 1x HDMI 2.1b, 3x DisplayPort 2.1a |
| HDMI | - | + |
API and SDK support
List of supported 3D and general-purpose computing APIs, including their specific versions.
| DirectX | 12 (12_1) | 12 Ultimate (12_2) |
| Shader Model | 6.4 | 6.8 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 1.2 | 2.2 |
| Vulkan | 1.2.131 | 1.3 |
| CUDA | 6.1 | - |
| 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 | 70−75
−65.2%
| 201 |
| 1440p | 35−40
−67.9%
| 109 |
| 4K | 24−27 | 67
+179%
|
Cost per frame, $
| 1080p | no data | 2.73 |
| 1440p | no data | 5.04 |
| 4K | no data | 8.19 |
FPS performance in popular games
Full HD
Low
| Atomic Heart | 190−200 | 190−200 |
| Counter-Strike 2 | 300−350 | 300−350 |
| Cyberpunk 2077 | 150−160 | 150−160 |
| Resident Evil 4 Remake | 180−190 | 180−190 |
Full HD
Medium
| Atomic Heart | 190−200 | 190−200 |
| Battlefield 5 | 160−170 | 160−170 |
| Counter-Strike 2 | 300−350 | 300−350 |
| Cyberpunk 2077 | 150−160 | 150−160 |
| Far Cry 5 | 299 | 299 |
| Fortnite | 290−300 | 290−300 |
| Forza Horizon 4 | 230−240 | 230−240 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 350−400 | 350−400 |
Full HD
High
| Atomic Heart | 190−200 | 190−200 |
| Battlefield 5 | 160−170 | 160−170 |
| Counter-Strike 2 | 300−350 | 300−350 |
| Counter-Strike: Global Offensive | 270−280 | 270−280 |
| Cyberpunk 2077 | 150−160 | 150−160 |
| Far Cry 5 | 289 | 289 |
| Fortnite | 290−300 | 290−300 |
| Forza Horizon 4 | 230−240 | 230−240 |
| Grand Theft Auto V | 160−170 | 160−170 |
| Metro Exodus | 150−160 | 150−160 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 438 | 438 |
| Valorant | 350−400 | 350−400 |
Full HD
Ultra
| Battlefield 5 | 160−170 | 160−170 |
| Cyberpunk 2077 | 150−160 | 150−160 |
| Far Cry 5 | 274 | 274 |
| Forza Horizon 4 | 230−240 | 230−240 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| The Witcher 3: Wild Hunt | 240 | 240 |
| Valorant | 350−400 | 350−400 |
Full HD
Epic
| Fortnite | 290−300 | 290−300 |
1440p
High
| Counter-Strike 2 | 180−190 | 180−190 |
| Counter-Strike: Global Offensive | 450−500 | 450−500 |
| Grand Theft Auto V | 130−140 | 130−140 |
| Metro Exodus | 100−110 | 100−110 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 400−450 | 400−450 |
1440p
Ultra
| Battlefield 5 | 150−160 | 150−160 |
| Cyberpunk 2077 | 85−90 | 85−90 |
| Far Cry 5 | 244 | 244 |
| Forza Horizon 4 | 200−210 | 200−210 |
| The Witcher 3: Wild Hunt | 184 | 184 |
1440p
Epic
| Fortnite | 150−160 | 150−160 |
4K
High
| Atomic Heart | 55−60 | 55−60 |
| Counter-Strike 2 | 80−85 | 80−85 |
| Grand Theft Auto V | 150−160 | 150−160 |
| Metro Exodus | 65−70 | 65−70 |
| The Witcher 3: Wild Hunt | 154 | 154 |
| Valorant | 300−350 | 300−350 |
4K
Ultra
| Battlefield 5 | 110−120 | 110−120 |
| Counter-Strike 2 | 80−85 | 80−85 |
| Cyberpunk 2077 | 40−45 | 40−45 |
| Far Cry 5 | 133 | 133 |
| Forza Horizon 4 | 150−160 | 150−160 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 95−100 | 95−100 |
4K
Epic
| Fortnite | 75−80 | 75−80 |
This is how Tesla P4 and RX 9070 compete in popular games:
- RX 9070 is 187% faster in 1080p
- RX 9070 is 211% faster in 1440p
- RX 9070 is 179% faster in 4K
All in all, in popular games:
- there's a draw in 59 tests (100%)
Pros & cons summary
| Performance score | 21.87 | 60.94 |
| Recency | 13 September 2016 | 6 March 2025 |
| Maximum RAM amount | 8 GB | 16 GB |
| Chip lithography | 16 nm | 5 nm |
| Power consumption (TDP) | 75 Watt | 220 Watt |
Tesla P4 has 66% lower power consumption.
RX 9070, on the other hand, has a 179% higher aggregate performance score, an age advantage of 8 years, a 100% higher maximum VRAM amount, and a 69% more advanced lithography process.
The Radeon RX 9070 is our recommended choice as it beats the Tesla P4 in performance tests.
Be aware that Tesla P4 is a workstation graphics card while Radeon RX 9070 is a desktop one.
Other comparisons
We selected several comparisons of graphics cards with performance close to those reviewed, providing you with more options to consider.
