L40

Graphics processor

Video memory: 48 GB^*
Memory bus: 384 bit^*
Rated memory bandwidth: 864 GB/s^*

No matched benchmark results are available for this entry yet.

Processing & platform

Architecture: Ada Lovelace^*
Process node: 5 nm^*
GPU base clock: 735 MHz^*
GPU boost clock: 2,490 MHz^*

Memory & storage

Video memory: 48 GB^*
Video memory type: GDDR6^*
Memory bus: 384 bit^*
Rated memory bandwidth: 864 GB/s^*

System configuration

Detailed specifications

Specifications 1 · 17 fields

GPU architecture — NVIDIA L40 — 48 GB GDDR6: Ada Lovelace^*
Theoretical peak: BF16 tensor dense per GPU — NVIDIA L40 — 48 GB GDDR6: 181.05^* TFLOPS
Theoretical peak: FP16 tensor dense per GPU — NVIDIA L40 — 48 GB GDDR6: 181.05^* TFLOPS
Theoretical peak: FP32 non-tensor dense per GPU — NVIDIA L40 — 48 GB GDDR6: 90.5^* TFLOPS
Native hardware support: FP4 tensor — NVIDIA L40 — 48 GB GDDR6: No^*
Native hardware support: FP6 tensor — NVIDIA L40 — 48 GB GDDR6: No^*
Theoretical peak: FP8 tensor dense per GPU — NVIDIA L40 — 48 GB GDDR6: 362^* TFLOPS
Theoretical peak: INT8 tensor dense per GPU — NVIDIA L40 — 48 GB GDDR6: 362^* TOPS
Theoretical peak: TF32 tensor dense per GPU — NVIDIA L40 — 48 GB GDDR6: 90.5^* TFLOPS
Physical configuration — NVIDIA L40 — 48 GB GDDR6: PCIe, dual-slot FHFL^*
Native hardware support for GPU interconnect — NVIDIA L40 — 48 GB GDDR6: No^*
PCIe interface declaration — NVIDIA L40 — 48 GB GDDR6: PCIe Gen4 x16^*
Maximum board power — NVIDIA L40 — 48 GB GDDR6: 300^* W
Peak memory bandwidth per GPU — NVIDIA L40 — 48 GB GDDR6: 864^* GB/s
Memory capacity per GPU — NVIDIA L40 — 48 GB GDDR6: 48^* GB
Memory technology — NVIDIA L40 — 48 GB GDDR6: GDDR6^*
GPU model — NVIDIA L40 — 48 GB GDDR6: NVIDIA L40^*

Specifications 2 · 8 fields

Product Name: L40^*
GPU Chip: AD102^*
Released: Oct 13th, 2022^*
Bus: PCIe 4.0 x16^*
Memory: 48 GB, GDDR6, 384 bit^*
GPU clock: 735^* MHz
Memory clock: 2,250^* MHz
Shaders TMUs ROPs: 18176 / 568 / 192^*

Specifications 3 · 8 fields

Product Name: L40^*
GPU Chip: AD102^*
Released: Oct 13th, 2022^*
Bus: PCIe 4.0 x16^*
Memory: 48 GB, GDDR6, 384 bit^*
GPU clock: 735^* MHz
Memory clock: 2,250^* MHz
Shaders / TMUs / ROPs: 18176 / 568 / 192^*

Specifications 4 · 60 fields

Brand: NVIDIA^*
Top BUS WIDTH: 384^* bit
Graphics Processor GPU Name: AD102^*
Graphics Processor Architecture: Ada Lovelace^*
Render Config SM Count: 142^*
Graphics Features CUDA: 8.9^*
Render Config Tensor Cores: 568^*
Graphics Processor Process Size: 5^* nm
Graphics Processor Transistors: 76,300 million^*
Graphics Processor Die Size: 609^* mm²
Graphics Card Release Date: Oct 13th, 2022^*
Graphics Card Generation: Server Ada (Lxx)^*
Graphics Card Successor: Server Hopper^*
Graphics Card Production: Active^*
Name: L40^*
Graphics Card Bus Interface: PCIe 4.0 x16^*
Clock Speeds Memory Clock: 2250 MHz 18 Gbps effective^*
Memory Memory Size: 48^* GB
Memory Memory Type: GDDR6^*
Memory Memory Bus: 384^* bit
Memory Bandwidth: 864^* GB/s
Render Config TMUs: 568^*
Top GRAPHICS PROCESSOR: AD102^*
Render Config ROPs: 192^*
Theoretical Performance Pixel Rate: 478.1 GPixel/s
Theoretical Performance Texture Rate: 1,414.3 GTexel/s
Board Design Slot Width: Dual-slot^*
Board Design TDP: 300^* W
Board Design Suggested PSU: 700^* W
Board Design Outputs: 4x DisplayPort 1.4a^*
Board Design Board Number: PG133 SKU 250^*
Graphics Features DirectX: 12 Ultimate (12_2)^*
Graphics Features OpenGL: 4.6^*
Graphics Features OpenCL: 3^*
Graphics Features Vulkan: 1.3^*
source file: nvidia2022.json^*
Graphics Processor Foundry: TSMC^*
Graphics Card Predecessor: Server Ampere^*
Recommended Resolutions: Good:1920x1080 | Good:2560x1440 | Good:3840x2160^*
Board Design Length: 267 mm 10.5 inches^*
Graphics Processor GPU Variant: AD102-895-A1^*
Board Design Power Connectors: 1x 16-pin^*
Graphics Processor Density: 125.3M / mm²^*
Board Design Height: 111 mm 4.4 inches^*
Top TMUS: 568^*
Top ROPS: 192^*
Clock Speeds Base Clock: 735^* MHz
Clock Speeds Boost Clock: 2,490^* MHz
Graphics Features Shader Model: 6.8^*
Top CORES: 18,176^*
Render Config Shading Units: 18,176^*
Render Config L2 Cache: 96^* MB
Top MEMORY SIZE: 48^* GB
Theoretical Performance FP32 (float): 90.52^* TFLOPS
Theoretical Performance FP64 (double): 1,414.3 GFLOPS (1:64)
Render Config L1 Cache: 128 KB (per SM)^*
Theoretical Performance FP16 (half): 90.52 TFLOPS (1:1)
Graphics Card Availability: 2,022^*
Top MEMORY TYPE: GDDR6^*
Render Config RT Cores: 142^*

Specifications 5 · 14 fields

manufacturer: NVIDIA^*
rop: 96^*
igp: No^*
bus: PCIe 4.0 x16^*
memType: GDDR6^*
gpuChip: GA102^*
productName: L40^*
releaseYear: 2,022^*
memSize: 48^*
memBusWidth: 384^*
gpuClock: 1,050^*
memClock: 2,000^*
unifiedShader: 7,168^*
tmu: 224^*

* Provisional data