NVIDIA GB200

GB200

NVIDIA GB200 Full Specs

37,888 Shaders
2.11GHz
372GB HBM3e16TB/s
··
160 TFLOPS
Form Factor
Superchip
TDP
2400W

GB200GB20040 PFLOPSMXFP4 Tensor Sparse (2x 20 PFLOPS)
x1
3.35 PFLOPS FP4 Tensor Sparse
x0.08

Clock Speed
··
Peak OPS
40 PFLOPSMXFP4 Tensor Sparse
Tensor FP4
20 PFLOPS
FP4 Tensor Sparse
40 PFLOPS
MXFP4 Tensor
20 PFLOPS
MXFP4 Tensor Sparse
40 PFLOPS
NVFP4 Tensor
20 PFLOPS
NVFP4 Tensor Sparse
40 PFLOPS
FP6 Tensor
10 PFLOPS
FP6 Tensor Sparse
20 PFLOPS
MXFP6 Tensor
10 PFLOPS
MXFP6 Tensor Sparse
20 PFLOPS
Tensor FP8-16
10 PFLOPS
FP8-16 Tensor Sparse
20 PFLOPS
Tensor FP8-32
10 PFLOPS
FP8-32 Tensor Sparse
20 PFLOPS
MXFP8 Tensor
10 PFLOPS
MXFP8 Tensor Sparse
20 PFLOPS
FP16
160 TFLOPS
Tensor FP16-16
5 PFLOPS
FP16-16 Tensor Sparse
10 PFLOPS
Tensor FP16-32
5 PFLOPS
FP16-32 Tensor Sparse
10 PFLOPS
BF16
160 TFLOPS
Tensor BF16
5 PFLOPS
BF16 Tensor Sparse
10 PFLOPS
Tensor TF32
2.5 PFLOPS
TF32 Tensor Sparse
5 PFLOPS
FP32
160 TFLOPS
FP64
80.02 TFLOPS
Tensor FP64
78.13 TFLOPS
Tensor INT8
10 POPS
INT8 Tensor Sparse
20 POPS
Pixel Rate
67.6 GPixel/s
Texture Rate
1.25 TTexel/s

Shaders
37,888 Shaders
TMUs
1,184 TMUs
ROPs
64 ROPs
Tensor Cores
1,184 T-Cores
SMs
296 SMs

Boost Clock
2.11GHz
Tensor Clock
2.06GHz

L1
64KB/SM Tex
L2 Cache
126MB shared

372GB HBM3e
Memory Bus
8192-bit
Memory Speed
7.8GT/s
Memory Bandwidth
16TB/s
ECC
Yes

TDP
2400W

Adaptive Sync
G-Sync
FreeSync
DSC
Not Supported

OpenCL
3
CUDA
10
PureVideo HD
VP13
VDPAU
Feature Set M

Decoder
7x NVDEC 6
Codec
MPEG-1
MPEG-2
MPEG-4
VC-1
VP8
VP9
AVC (H.264)
HEVC (H.265)
AV1

Form Factor
Superchip
PCIe
PCIe 6.0 x16
Cooling
Liquid
Multi-GPU
Multi-GPU Support
Supported
Multi-GPU Type
NVLink

Manufacturer
Chip Designer
Architecture
Family
Branding
GB200 branding
Codename
NV190
Chip Variant
Umbriel
Market Segment
Server
Release Date
Mar 18, 2024

Foundry
TSMC
Fabrication Node
4NP
Die Size
3240mm²
Transistor Count
416B
Transistor Density
128.4 MTr/mm²