NVIDIA GB200 vs NVIDIA L4 Full Specs

Summary

37,888 Shaders 2.11GHz	7,680 Shaders 2.04GHz
384GB HBM3e16TB/s	24GB GDDR6300.1GB/s
Peak·FP32·FP16 160 TFLOPS	Peak·FP32·FP16 31.33 TFLOPS
Form Factor Superchip	Form Factor PCIe Card
TDP 2700W	TDP 72W
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Highlights

Peak OPS

Peak OPS FP32 FP16 Tensor FP4 FP4 Tensor Sparse 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 Tensor FP64 BF16 Tensor BF16 BF16 Tensor Sparse Tensor TF32 Tensor INT8 Tensor INT4 Memory Bandwidth TDP

GB20040 PFLOPSFP4 Tensor Sparse (2x 20 PFLOPS)

x39.89

L41 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed2112MHz UC·Boost·OC	Clock Speed2040MHz UC·Base·Boost·OC
Peak OPS 40 PFLOPSFP4 Tensor Sparse	Peak OPS 1 POPSINT4 Tensor Sparse
Tensor FP4 20 PFLOPS FP4 Tensor Sparse 40 PFLOPS	-
Tensor FP8-16 10 PFLOPS FP8-16 Tensor Sparse 20 PFLOPS Tensor FP8-32 10 PFLOPS FP8-32 Tensor Sparse 20 PFLOPS	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 FP16-16 5 PFLOPS FP16-16 Tensor Sparse 10 PFLOPS Tensor FP16-32 5 PFLOPS FP16-32 Tensor Sparse 10 PFLOPS	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
BF16 320.1 TFLOPS Tensor BF16 5 PFLOPS BF16 Tensor Sparse 10 PFLOPS	BF16 31.33 TFLOPS Tensor BF16 62.67 TFLOPS BF16 Tensor Sparse 125.3 TFLOPS
Tensor TF32 2.5 PFLOPS	Tensor TF32 31.33 TFLOPS
FP32 160 TFLOPS	FP32 31.33 TFLOPS
FP64 80.02 TFLOPS Tensor FP64 78.13 TFLOPS	FP64 489.6 GFLOPS Tensor FP64 -
Tensor INT4 -	Tensor INT4 501.4 TOPS
Tensor INT8 10 POPS	Tensor INT8 250.7 TOPS
Ray -	Ray 72.43 TOPS
Pixel Rate 67.6 GPixel/s	Pixel Rate 163.2 GPixel/s
Texture Rate 1.25 TTexel/s	Texture Rate 489.6 GTexel/s

Core Config

Shaders 37,888 Shaders	Shaders 7,680 Shaders
TMUs 1,184 TMUs	TMUs 240 TMUs
ROPs 64 ROPs	ROPs 80 ROPs
Tensor Cores 1,184 T-Cores	Tensor Cores 240 T-Cores
RT Cores -	RT Cores 60 RT-Cores
SMs 296 SMs	SMs 60 SMs

Clocks

Base Clock -	Base Clock 795MHz
Boost Clock 2.11GHz	Boost Clock 2.04GHz
Tensor Clock 2.06GHz	Tensor Clock -

Cache

L2 Cache 65.5MB shared

L2 Cache 49.1MB shared

Memory

384GB HBM3e	24GB GDDR6
Memory Bus 8192-bit	Memory Bus 192-bit
Memory Speed 7.8GT/s	Memory Speed 12.5GT/s
Memory Bandwidth 16TB/s	Memory Bandwidth 300.1GB/s

Power & Thermals

TDP 2700W

TDP 72W

Encoder

-	Encoder Model 2x NVENC 8

Decoder

Decoder Model 7x NVDEC 6

Decoder Model NVDEC 5

Card

Form Factor Superchip	Form Factor PCIe Card
PCIe -	PCIe 1-Slots
-	Height 56 mm (2.21") Width 169 mm (6.65") Depth 20 mm (0.79")
Cooling Passive	Cooling Passive
Power Connectors -	Power Connectors 1x 16-Pin 12VHPWR

Chip

Manufacturer NVIDIA	Manufacturer NVIDIA
Chip Designer NVIDIA	Chip Designer NVIDIA
Architecture Blackwell	Architecture Ada Lovelace
Family Server	Family Server
Branding	Branding
Codename NV190	Codename NV184
Chip Variant Umbriel	Chip Variant AD104-250
Market Segment Server	Market Segment Server
Release Date Mar 18, 2024	Release Date Mar 21, 2023

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4NP	Fabrication Node 4N
Die Size 1620mm²	Die Size 295mm²
Transistor Count 208 Billion	Transistor Count 35.8 Billion
Transistor Density 128.4 MTr/mm²	Transistor Density 121.6 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAGB200 vs GPU NVIDIAB200 NVIDIAGB200 vs GPU NVIDIAB100 NVIDIAGB200 vs GPU AMDInstinct MI300X Show 8 more

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