Explore the complete details of L40S VS Radeon Pro Vega 64, including specs, performance benchmarks
GeForce RTX 4090
NVIDIAGeForce RTX 5090 D
NVIDIAGeForce RTX 5080
NVIDIAQuadro K5000
NVIDIAIris Xe Graphics G7
IntelGraphics 4-Cores iGPU (Arc)
IntelGeForce GTX 570
NVIDIAGraphics 4-Core iGPU (Arc)
UnknownRadeon RX 460 Mobile
AMDGeForce GTX 750 Ti
NVIDIAGRID M60-8Q
NVIDIARadeon HD 7850
AMDThe L40S GPU by NVIDIA. features a Ada Lovelace (2022−2024) architecture. with 18176 CUDA cores. and a boost clock of 2520 MHz MHz. It offers GDDR6 memory with 48 GB GB capacity and a 384 Bit-bit interface. delivering a bandwidth of 864.0 GB/s GB/s. With a power consumption (TDP) of 300W. it supports DirectX 12 Ultimate (12_2), Vulkan 1.3, DLSS 1 for enhanced performance.
The L40S GPU by NVIDIA. features a Ada Lovelace (2022−2024) architecture. with 18176 CUDA cores. and a boost clock of 2520 MHz MHz. It offers GDDR6 memory with 48 GB GB capacity and a 384 Bit-bit interface. delivering a bandwidth of 864.0 GB/s GB/s. With a power consumption (TDP) of 300W. it supports DirectX 12 Ultimate (12_2), Vulkan 1.3, DLSS 1 for enhanced performance.
Basic details about the L40S, including manufacturer, ranking, and release date.
|
![]() |
|
---|---|---|
Manufacturer | NVIDIA | AMD |
Ranking | 71 | 174 |
Popularity Rank | not in top-100 | not in top-100 |
Architecture | Ada Lovelace (2022−2024) | GCN 5.0 (2017−2020) |
GPU code name | AD102 | Vega 10 |
Market Segmente | Workstation | Workstation |
Length - Width | 267 mm - 2-slot | 267 mm - IGP |
Release Date | 13 October 2022 | 27 June 2017 |
PerformanceDetails on clock speeds, cores, and floating-point processing power of L40S VS Radeon Pro Vega 64. |
||
Core Clock Speed | 1110 MHz | 1250 MHz |
Boost Clock Speed | 2520 MHz | 1350 MHz |
Floating Point Processing Power | 91.61 TFLOPS | 11.06 TFLOPS |
No of Transistors | 76,300 million | 12,500 million |
CUDA Cores | 18176 | 4096 |
Ray Tracing Cores | 142 | N/A |
Tensor Cores | 568 | N/A |
Texture Fill Rate | 1,431 | 345.6 |
ROPs | 192 | 64 |
Available display connectors and API compatibility for enhanced performance.
|
![]() |
|
---|---|---|
Interface | PCIe 4.0 x16 | PCIe 3.0 x16 |
Display Connectors | 1x HDMI 2.1, 3x DisplayPort 1.4a | No outputs |
HDMI | 1 | N/A |
DirectX | 12 Ultimate (12_2) | 12 (12_1) |
Shader Model | 6.7 | 6.4 |
OpenGL | 4.6 | 4.6 |
OpenCL | 3.0 | 2.0 |
Vulkan | 1.3 | 1.1.125 |
CUDA | 8.9 | N/A |
DLSS | 1 | N/A |
TMUs | 568 | 256 |
Memory & BusInformation on memory type, capacity, and bandwidth to evaluate data processing power. |
||
Memory Type | GDDR6 | HBM2 |
Maximum RAM | 48 GB | 16 GB |
Memory Bus Width | 384 Bit | 2048 Bit |
Memory Clock Speed | 2250 MHz | 786 MHz |
Memory Bandwidth | 864.0 GB/s GB/s | 402.4 GB/s GB/s |
Resizable BAR | 1 | N/A |
Power & EfficiencyPower consumption, efficiency, and additional power requirements. |
||
Power Consumption (TDP) | 300 W | 250 W |
Power Efficiency | 11.14 | 9.15 |
Manufacturing Process | 5 nm | 14 nm |
Supplementary Power Connectors | 1x 16-pin | None |
Here are some of the closest competitors to this GPU. Compare their power consumption, efficiency, and additional power requirements.
Here are some of the closest competitors to this GPU. Compare their power consumption, efficiency, and additional power requirements.