GPU

NVIDIA GeForce RTX 3090 Ti

Edit@2 months ago

Intergrated Memory(VRAM)
Capacity

24 GB

(GDDR6X 384-bit)

Bandwidth

1008 GB/s

144 Token/s

Vector Compute
FP64
625 G
FP32
40 T
FP16
40 T
BF16
40 T
INT32
20 T
INT8
X

NVIDIA GeForce RTX 3090 Ti General-Purpose Float-Point performance (Vector Performance / Scalar Performance)

FP64: 625 GFLOPS

FP32: 40 TFLOPS

FP16: 40 TFLOPS

BF16: 40 TFLOPS

INT32: 20 TOPS

Matirx Compute
FP64
X
FP32
X
FP16
79.99 T
159.99 T
FP8
X
TF32
40.00 T
79.99 T
BF16
79.99 T
159.99 T
INT16
X
INT8
319.98 T
639.96 T
INT4
639.96 T
1279.92 T

NVIDIA GeForce RTX 3090 Ti AI performance (Tensor Performance / Matrix Performance)

FP16: 79.99 TFLOPS, with sparsity: 159.99 TFLOPS

TF32: 40.00 TFLOPS, with sparsity: 79.99 TFLOPS

BF16: 79.99 TFLOPS, with sparsity: 159.99 TFLOPS

INT8: 319.98 TOPS, with sparsity: 639.96 TOPS

INT4: 639.96 TOPS, with sparsity: 1279.92 TOPS

Hardware Specs
NVIDIA GeForce RTX 3090 Ti is a 8nm chip, has 28300 million transistors, launched by NVIDIA at 2022. It has 24 GB built-in(On-Board/On-Chip) memory with bandwidth up to 1008 GB/s. It has 10752 general-purpose ALUs(CUDA cores/Shader cores) and 336 matrix cores(Tensor cores) .
Process Node
8 nm
Launch Year
2022
Vector(CUDA) Cores
10752
Matrix(Tensor) Cores
336
Core Frequency
1560 ~ 1860 MHz
Cache
6MB

Comment without registration

Share your experience with NVIDIA GeForce RTX 3090 Ti / Found an Error? Help Us Improve!