GPU

NVIDIA TITAN RTX

Edit@1 months ago

Intergrated Memory(VRAM)
Capacity

24 GB

(GDDR6 384-bit)

Bandwidth

672 GB/s

96 Token/s

Vector Compute
FP64
509.80 G
FP32
16.31 T
FP16
32.62 T
BF16
X
INT32
NI
INT8
X

NVIDIA TITAN RTX General-Purpose Float-Point performance (Vector Performance / Scalar Performance)

FP64: 509.80 GFLOPS

FP32: 16.31 TFLOPS

FP16: 32.62 TFLOPS

Matirx Compute
FP64
X
FP32
X
FP16
65.25 T
FP8
X
TF32
X
BF16
X
INT16
X
INT8
261.00 T
INT4
521.99 T

NVIDIA TITAN RTX AI performance (Tensor Performance / Matrix Performance)

FP16: 65.25 TFLOPS

INT8: 261.00 TOPS

INT4: 521.99 TOPS

Hardware Specs
NVIDIA TITAN RTX is a 12nm chip, has 18600 million transistors, launched by NVIDIA at 2018. It has 24 GB built-in(On-Board/On-Chip) memory with bandwidth up to 672 GB/s. It has 4608 general-purpose ALUs(CUDA cores/Shader cores) and 576 matrix cores(Tensor cores) .
Process Node
12 nm
Launch Year
2018
Vector(CUDA) Cores
4608
Matrix(Tensor) Cores
576
Core Frequency
1350 ~ 1770 MHz
Cache
6MB

Comment without registration

Share your experience with NVIDIA TITAN RTX / Found an Error? Help Us Improve!