GPU Comparison

NVIDIA

GEFORCE

NVIDIA B200

CORE STATE GB100

VRAM 90 GB

CLOCK SPEED 1965 MHz

TDP 1000 W

BUS WIDTH 4096 bit

ARCHITECTURE Blackwell

nm

PROCESS 5 nm

LAUNCH DATE —

VS

NVIDIA

GEFORCE

Quadro M4000

CORE STATE GM204

VRAM 8 GB

CLOCK SPEED —

TDP 120 W

BUS WIDTH 256 bit

ARCHITECTURE Maxwell 2.0

nm

PROCESS 28 nm

LAUNCH DATE 2015

PERFORMANCE BENCHMARKS

geekbench_opencl

345,482

19,045

3dmark_3dmark_steel_nomad_dx12

N/A

680

geekbench_vulkan

N/A

24,640

passmark_directx_10

N/A

33

passmark_directx_11

N/A

49

passmark_directx_12

N/A

26

passmark_directx_9

N/A

113

passmark_g2d

N/A

673

passmark_g3d

N/A

6,680

passmark_gpu_compute

N/A

2,660

DETAILED SPECIFICATIONS

SPECIFICATION

B200

Quadro M4000

Core Specs

Shading Units

18,944

1,664 -91.2%

Shaders

18,944

1,664 -91.2%

TMUs

592

104 -82.4%

ROPs

24

64 +166.7%

SM Count

148

—

Clocks

Base Clock

700 MHz

—

Boost Clock

1965 MHz

—

GPU Clock

—

773 MHz

Memory Clock

2000 MHz 8 Gbps effective

1502 MHz 6 Gbps effective

Memory

Memory Size

90 GB

8 GB

VRAM (MB)

92,160

8,192 -91.1%

Memory Type

HBM3e

GDDR5

Memory Bus

4096 bit

256 bit

Bandwidth

4.10 TB/s

192.3 GB/s

Cache

L1 Cache

256 KB (per SM)

48 KB (per SMM)

L2 Cache

50 MB

2 MB

Performance

Pixel Rate

47.16 GPixel/s

49.47 GPixel/s

Texture Rate

1,163.3 GTexel/s

80.39 GTexel/s

FP32 (TFLOPS)

74.45 TFLOPS

2.573 TFLOPS

FP64 (TFLOPS)

37.22 TFLOPS (1:2)

80.39 GFLOPS (1:32)

FP16 (TFLOPS)

1,191.2 TFLOPS (16:1)

—

AI/RT

Tensor Cores

592

—

Power

TDP

1000 W

120 W

TDP (W)

1,000

120 -88.0%

Suggested PSU

1400 W

300 W

Power Connectors

—

1x 6-pin

Architecture

Architecture

Blackwell

Maxwell 2.0

GPU Name

GB100

GM204

Generation

Server Blackwell (Bxx)

Quadro Maxwell (Mx000)

Process Size

5 nm

28 nm

Transistors

104,000 million

5,200 million

Die Size

—

398 mm²

Foundry

TSMC

TSMC

Density

—

13.1M / mm²

API Support

DirectX

—

12 (12_1)

OpenGL

—

4.6

Vulkan

—

1.4

OpenCL

3.0

3.0

CUDA

10.0

5.2

Shader Model

—

6.8

Physical

Slot Width

SXM Module

Single-slot

Length

—

241 mm 9.5 inches

Height

—

111 mm 4.4 inches

Outputs

No outputs

4x DisplayPort 1.2

Bus Interface

PCIe 5.0 x16

PCIe 3.0 x16

Other

Production

Active

End-of-life

Predecessor

Server Hopper

Quadro Kepler

Successor

Server Rubin

Quadro Pascal

View B200 Details View Quadro M4000 Details