NVIDIA L4 vs NVIDIA L40 Full Specs

Summary

7,680 Shaders 2.04GHz	18,176 Shaders 2.49GHz
24GB GDDR6300.1GB/s	48GB GDDR6864GB/s
Peak·FP32·FP16 31.33 TFLOPS	Peak·FP32·FP16 90.52 TFLOPS
Form Factor PCIe Card	Form Factor PCIe Card
TDP 72W	TDP 300W
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 1x 16-Pin 12VHPWR

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP8-16 FP8-16 Tensor Sparse Tensor FP8-32 FP8-32 Tensor Sparse Tensor FP16-16 FP16-16 Tensor Sparse Tensor FP16-32 FP16-32 Tensor Sparse FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

L41 POPSINT4 Tensor Sparse

x1

L402.9 POPSINT4 Tensor Sparse

x2.89

Show Top Score

Theoretical Performance

Clock Speed2040MHz UC·Base·Boost·OC	Clock Speed2490MHz UC·Base·Boost·OC
Peak OPS 1 POPSINT4 Tensor Sparse	Peak OPS 2.9 POPSINT4 Tensor Sparse
Tensor FP8-16 250.7 TFLOPS FP8-16 Tensor Sparse 501.4 TFLOPS Tensor FP8-32 125.3 TFLOPS FP8-32 Tensor Sparse 250.7 TFLOPS	Tensor FP8-16 724.1 TFLOPS FP8-16 Tensor Sparse 1.45 PFLOPS Tensor FP8-32 362.1 TFLOPS FP8-32 Tensor Sparse 724.1 TFLOPS
Tensor FP16-16 125.3 TFLOPS FP16-16 Tensor Sparse 250.7 TFLOPS Tensor FP16-32 62.67 TFLOPS FP16-32 Tensor Sparse 125.3 TFLOPS	Tensor FP16-16 362.1 TFLOPS FP16-16 Tensor Sparse 724.1 TFLOPS Tensor FP16-32 181 TFLOPS FP16-32 Tensor Sparse 362.1 TFLOPS
BF16 31.33 TFLOPS Tensor BF16 62.67 TFLOPS BF16 Tensor Sparse 125.3 TFLOPS	BF16 90.52 TFLOPS Tensor BF16 181 TFLOPS BF16 Tensor Sparse 362.1 TFLOPS
Tensor TF32 31.33 TFLOPS	Tensor TF32 90.52 TFLOPS
FP32 31.33 TFLOPS	FP32 90.52 TFLOPS
FP64 489.6 GFLOPS	FP64 1.41 TFLOPS
Tensor INT4 501.4 TOPS	Tensor INT4 1.45 POPS
Tensor INT8 250.7 TOPS	Tensor INT8 724.1 TOPS
Ray 72.43 TOPS	Ray 209.2 TOPS
Pixel Rate 163.2 GPixel/s	Pixel Rate 478.1 GPixel/s
Texture Rate 489.6 GTexel/s	Texture Rate 1.41 TTexel/s

Core Config

Shaders 7,680 Shaders	Shaders 18,176 Shaders
TMUs 240 TMUs	TMUs 568 TMUs
ROPs 80 ROPs	ROPs 192 ROPs
Tensor Cores 240 T-Cores	Tensor Cores 568 T-Cores
RT Cores 60 RT-Cores	RT Cores 142 RT-Cores
SMs 60 SMs	SMs 142 SMs

Clocks

Base Clock 795MHz	Base Clock 735MHz
Boost Clock 2.04GHz	Boost Clock 2.49GHz

Cache

L2 Cache 49.1MB shared

L2 Cache 98.3MB shared

Memory

24GB GDDR6	48GB GDDR6
Memory Bus 192-bit	Memory Bus 384-bit
Memory Speed 12.5GT/s	Memory Speed 18GT/s
Memory Bandwidth 300.1GB/s	Memory Bandwidth 864GB/s

Power & Thermals

TDP 72W

TDP 300W

Video Output

Multi-Monitor -	Multi-Monitor 4
HDCP -	HDCP HDCP 2.3

Ports

-	4x DisplayPort 1.4

Encoder

Encoder Model 2x NVENC 8

Encoder Model 2x NVENC 8

Decoder

Decoder Model NVDEC 5

Decoder Model NVDEC 5

Card

Form Factor PCIe Card	Form Factor PCIe Card
PCIe 1-Slots	PCIe 2-Slots
Height 56 mm (2.21") Width 169 mm (6.65") Depth 20 mm (0.79")	Height 111 mm (4.37") Width 267 mm (10.51") Depth 40 mm (1.57")
Cooling Passive	Cooling Passive
Power Connectors 1x 16-Pin 12VHPWR	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Ada Lovelace	Architecture Ada Lovelace
Family Server	Family Server
Branding	Branding
Codename NV184	Codename NV182
Chip Variant AD104-250	Chip Variant AD102-200-A1
Market Segment Server	Market Segment Server
Release Date Mar 21, 2023	Release Date Oct 13, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4N	Fabrication Node 4N
Die Size 295mm²	Die Size 608mm²
Transistor Count 35.8 Billion	Transistor Count 76.3 Billion
Transistor Density 121.6 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAL4 vs GPU NVIDIARTX 4000 Ada NVIDIAL4 vs GPU NVIDIARTX 4500 Ada NVIDIAL4 vs GPU NVIDIARTX PRO 4000 Blackwell SFF Show 12 more

NVIDIAL40 vs GPU NVIDIAB200 NVIDIAL40 vs GPU NVIDIAGB200 NVIDIAL40 vs GPU NVIDIARTX PRO 5000 Blackwell Show 12 more