NVIDIA B200 vs NVIDIA L40 Full Specs

Summary

18,944 Shaders 1.98GHz	18,176 Shaders 2.49GHz
192GB HBM3e7.7TB/s	48GB GDDR6864GB/s
Peak·FP32·FP16 75.02 TFLOPS	Peak·FP32·FP16 90.52 TFLOPS
Form Factor SXM6	Form Factor PCIe Card
TDP 1000W	TDP 300W
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

B20018 PFLOPSFP4 Tensor Sparse

x6.22

L402.9 POPSINT4 Tensor Sparse

x1

Show Top Score

Theoretical Performance

Clock Speed1980MHz UC·Boost·OC	Clock Speed2490MHz UC·Base·Boost·OC
Peak OPS 18 PFLOPSFP4 Tensor Sparse	Peak OPS 2.9 POPSINT4 Tensor Sparse
Tensor FP4 9 PFLOPS FP4 Tensor Sparse 18 PFLOPS	-
Tensor FP8-16 4.5 PFLOPS FP8-16 Tensor Sparse 9 PFLOPS Tensor FP8-32 4.5 PFLOPS FP8-32 Tensor Sparse 9 PFLOPS	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 2.25 PFLOPS FP16-16 Tensor Sparse 4.5 PFLOPS Tensor FP16-32 2.25 PFLOPS FP16-32 Tensor Sparse 4.5 PFLOPS	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 150 TFLOPS Tensor BF16 2.25 PFLOPS BF16 Tensor Sparse 4.5 PFLOPS	BF16 90.52 TFLOPS Tensor BF16 181 TFLOPS BF16 Tensor Sparse 362.1 TFLOPS
Tensor TF32 1.13 PFLOPS	Tensor TF32 90.52 TFLOPS
FP32 75.02 TFLOPS	FP32 90.52 TFLOPS
FP64 37.51 TFLOPS Tensor FP64 35.16 TFLOPS	FP64 1.41 TFLOPS Tensor FP64 -
Tensor INT4 -	Tensor INT4 1.45 POPS
Tensor INT8 4.5 POPS	Tensor INT8 724.1 TOPS
Ray -	Ray 209.2 TOPS
Pixel Rate 63.4 GPixel/s	Pixel Rate 478.1 GPixel/s
Texture Rate 1.17 TTexel/s	Texture Rate 1.41 TTexel/s

Core Config

Shaders 18,944 Shaders	Shaders 18,176 Shaders
TMUs 592 TMUs	TMUs 568 TMUs
ROPs 32 ROPs	ROPs 192 ROPs
Tensor Cores 592 T-Cores	Tensor Cores 568 T-Cores
RT Cores -	RT Cores 142 RT-Cores
SMs 148 SMs	SMs 142 SMs

Clocks

Base Clock -	Base Clock 735MHz
Boost Clock 1.98GHz	Boost Clock 2.49GHz
Tensor Clock 1.86GHz	Tensor Clock -

Cache

L2 Cache 65.5MB shared

L2 Cache 98.3MB shared

Memory

192GB HBM3e	48GB GDDR6
Memory Bus 8192-bit	Memory Bus 384-bit
Memory Speed 7.5GT/s	Memory Speed 18GT/s
Memory Bandwidth 7.7TB/s	Memory Bandwidth 864GB/s

Power & Thermals

TDP 1000W

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

Decoder

Decoder Model 7x NVDEC 6

Decoder Model NVDEC 5

Card

Form Factor SXM6	Form Factor PCIe Card
PCIe -	PCIe 2-Slots
-	Height 111 mm (4.37") Width 267 mm (10.51") Depth 40 mm (1.57")
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 NV182
Chip Variant Umbriel	Chip Variant AD102-200-A1
Market Segment Server	Market Segment Server
Release Date Mar 18, 2024	Release Date Oct 13, 2022

Fabrication

Foundry TSMC	Foundry TSMC
Fabrication Node 4NP	Fabrication Node 4N
Die Size 1620mm²	Die Size 608mm²
Transistor Count 208 Billion	Transistor Count 76.3 Billion
Transistor Density 128.4 MTr/mm²	Transistor Density 125.4 MTr/mm²

Images

No images available

No images available

Competitors

NVIDIAB200 vs GPU NVIDIAB100 NVIDIAB200 vs GPU NVIDIAGB200 NVIDIAB200 vs GPU AMDInstinct MI350X Show 8 more

NVIDIAL40 vs GPU NVIDIAGB200 NVIDIAL40 vs GPU NVIDIARTX PRO 5000 Blackwell NVIDIAL40 vs GPU NVIDIARTX 5880 Ada Show 12 more