Radeon RX 6650M vs Tesla P40
Aggregate performance score
We've compared Tesla P40 with Radeon RX 6650M, including specs and performance data.
6650M outperforms P40 by a substantial 31% 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 | 237 | 150 |
| Place by popularity | not in top-100 | not in top-100 |
| Cost-effectiveness evaluation | 1.02 | no data |
| Power efficiency | 8.64 | 23.62 |
| Architecture | Pascal (2016−2021) | RDNA 2.0 (2020−2025) |
| GPU code name | GP102 | Navi 23 |
| Market segment | Workstation | Laptop |
| Release date | 13 September 2016 (10 years ago) | 4 January 2022 (4 years ago) |
| Launch price (MSRP) | $5,699 | no data |
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 | 3840 | 1792 |
| Core clock speed | 1303 MHz | 2068 MHz |
| Boost clock speed | 1531 MHz | 2416 MHz |
| Number of transistors | 11,800 million | 11,060 million |
| Manufacturing process technology | 16 nm | 7 nm |
| Power consumption (TDP) | 250 Watt | 120 Watt |
| Texture fill rate | 367.4 | 270.6 |
| Floating-point processing power | 11.76 TFLOPS | 8.659 TFLOPS |
| ROPs | 96 | 64 |
| TMUs | 240 | 112 |
| Ray Tracing Cores | no data | 28 |
| L0 Cache | no data | 448 KB |
| L1 Cache | 1.4 MB | 512 KB |
| L2 Cache | 3 MB | 2 MB |
| L3 Cache | no data | 32 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 | no data | large |
| Interface | PCIe 3.0 x16 | PCIe 4.0 x8 |
| Length | 267 mm | no data |
| Width | 2-slot | no data |
| Supplementary power connectors | 8-pin EPS | 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 | 24 GB | 8 GB |
| Memory bus width | 384 Bit | 128 Bit |
| Memory clock speed | 1808 MHz | 2000 MHz |
| Memory bandwidth | 347.1 GB/s | 256.0 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 | No outputs |
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 | 6.7 | 6.5 |
| OpenGL | 4.6 | 4.6 |
| OpenCL | 3.0 | 2.1 |
| Vulkan | 1.3 | 1.3 |
| CUDA | 6.1 | - |
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 | 85−90
−26.1%
| 115 |
Cost per frame, $
| 1080p | 67.05 | no data |
FPS performance in popular games
Full HD
Low
| Counter-Strike 2 | 200−210 | 200−210 |
| Cyberpunk 2077 | 127 | 127 |
| Resident Evil 4 Remake | 95−100 | 95−100 |
Full HD
Medium
| Battlefield 5 | 120−130 | 120−130 |
| Counter-Strike 2 | 200−210 | 200−210 |
| Cyberpunk 2077 | 106 | 106 |
| Far Cry 5 | 110−120 | 110−120 |
| Fortnite | 54 | 54 |
| Forza Horizon 4 | 140−150 | 140−150 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 140−150 | 140−150 |
| Valorant | 220−230 | 220−230 |
Full HD
High
| Battlefield 5 | 120−130 | 120−130 |
| Counter-Strike 2 | 200−210 | 200−210 |
| Counter-Strike: Global Offensive | 270−280 | 270−280 |
| Cyberpunk 2077 | 79 | 79 |
| Dota 2 | 118 | 118 |
| Far Cry 5 | 110−120 | 110−120 |
| Far Cry 6 | 96 | 96 |
| Fortnite | 46 | 46 |
| Forza Horizon 4 | 140−150 | 140−150 |
| Grand Theft Auto V | 120−130 | 120−130 |
| Metro Exodus | 86 | 86 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 140−150 | 140−150 |
| The Witcher 3: Wild Hunt | 167 | 167 |
| Valorant | 220−230 | 220−230 |
Full HD
Ultra
| Battlefield 5 | 120−130 | 120−130 |
| Cyberpunk 2077 | 64 | 64 |
| Dota 2 | 100 | 100 |
| Far Cry 5 | 110−120 | 110−120 |
| Forza Horizon 4 | 140−150 | 140−150 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 140−150 | 140−150 |
| The Witcher 3: Wild Hunt | 90 | 90 |
| Valorant | 220−230 | 220−230 |
Full HD
Epic
| Fortnite | 40 | 40 |
1440p
High
| Counter-Strike 2 | 90−95 | 90−95 |
| Counter-Strike: Global Offensive | 250−260 | 250−260 |
| Far Cry 6 | 65−70 | 65−70 |
| Grand Theft Auto V | 75−80 | 75−80 |
| Metro Exodus | 50−55 | 50−55 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 170−180 | 170−180 |
| Valorant | 250−260 | 250−260 |
1440p
Ultra
| Battlefield 5 | 95−100 | 95−100 |
| Cyberpunk 2077 | 40−45 | 40−45 |
| Far Cry 5 | 85−90 | 85−90 |
| Forza Horizon 4 | 100−110 | 100−110 |
| The Witcher 3: Wild Hunt | 65−70 | 65−70 |
1440p
Epic
| Fortnite | 95−100 | 95−100 |
4K
High
| Counter-Strike 2 | 40−45 | 40−45 |
| Far Cry 6 | 27−30 | 27−30 |
| Grand Theft Auto V | 75−80 | 75−80 |
| Metro Exodus | 30−35 | 30−35 |
| The Witcher 3: Wild Hunt | 55−60 | 55−60 |
| Valorant | 220−230 | 220−230 |
4K
Ultra
| Battlefield 5 | 55−60 | 55−60 |
| Counter-Strike 2 | 40−45 | 40−45 |
| Cyberpunk 2077 | 18−20 | 18−20 |
| Dota 2 | 100−110 | 100−110 |
| Far Cry 5 | 45−50 | 45−50 |
| Forza Horizon 4 | 65−70 | 65−70 |
| PLAYERUNKNOWN'S BATTLEGROUNDS | 45−50 | 45−50 |
4K
Epic
| Fortnite | 45−50 | 45−50 |
This is how Tesla P40 and RX 6650M compete in popular games:
- RX 6650M is 35% faster in 1080p
All in all, in popular games:
- there's a draw in 61 tests (100%)
Pros & cons summary
| Performance score | 27.71 | 36.43 |
| Recency | 13 September 2016 | 4 January 2022 |
| Maximum RAM amount | 24 GB | 8 GB |
| Chip lithography | 16 nm | 7 nm |
| Power consumption (TDP) | 250 Watt | 120 Watt |
Tesla P40 has a 200% higher maximum VRAM amount.
RX 6650M, on the other hand, has a 31% higher aggregate performance score, an age advantage of 5 years, a 56% more advanced lithography process, and 52% lower power consumption.
The Radeon RX 6650M is our recommended choice as it beats the Tesla P40 in performance tests.
Be aware that Tesla P40 is a workstation graphics card while Radeon RX 6650M 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.
