NVIDIA GeForce RTX 4090 Ti Specs
NVIDIA GeForce RTX 4090 Ti
|
18432 Shaders
48GB GDDR6X
2625MHz
|
|
Peak Performance
3.1 POPS
INT4 Tensor Sparse
|
|
FP32
96.77 TFLOPS
|
|
FP16
96.77 TFLOPS
|
|
Form Factor
PCIe Card
3.0-Slots
|
|
TDP
600W
|
|
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
|
|
GB6 OpenCL N/A
0%
|
|
GB6 Metal N/A
0%
|
|
GB6 Vulkan N/A
0%
|
|
GB5 OpenCL N/A
0%
|
|
GB5 CUDA N/A
0%
|
|
GB5 Metal N/A
0%
|
|
GB5 Vulkan N/A
0%
|
|
OCT 2020.1 N/A
0%
|
|
OCT Metal N/A
0%
|
|
Manufacturer
NVIDIA
|
|
Chip Designer
NVIDIA
|
|
Architecture
Ada Lovelace
|
|
Family
GeForce 40
|
|
Codename
NV182
AD102
Variant
AD102-400-A1
|
|
Market Segment
Desktop
|
|
Release Date
Unknown
|
|
Foundry
TSMC
-
|
|
Fabrication Node
4N
-
|
|
Die Size
608 mm²
-
|
|
Transistor Count
76.3 Billion
-
|
|
Transistor Density
125.41M/mm²
-
|
|
Form
PCIe Card
|
|
Shading Units
18432 Shaders
-
|
|
Texture Mapping Units
576 TMUs
|
|
Render Output Units
176 ROPs
|
|
Tensor Cores
576 T-Cores
|
|
Ray-Tracing Cores
144 RT-Cores
|
|
Streaming Multiprocessors
144 SMs
|
|
-
-
|
|
-
-
|
|
Graphics Processing Clusters
12 GPCs
|
|
-
-
2355MHz Base
2625MHz
|
|
Peak Performance
3.1 POPS
INT4 Tensor Sparse
|
|
-
-
-
|
|
FP8
-
774.14 TFLOPS Tensor (FP16 Accumulate)
1.55 PFLOPS Tensor (FP16 Accumulate) Sparse
387.07 TFLOPS Tensor (FP32 Accumulate)
774.14 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP16
96.77 TFLOPS
387.07 TFLOPS Tensor (FP16 Accumulate)
774.14 TFLOPS Tensor (FP16 Accumulate) Sparse
193.54 TFLOPS Tensor (FP32 Accumulate)
387.07 TFLOPS Tensor (FP32 Accumulate) Sparse
|
|
FP32
96.77 TFLOPS
-
-
|
|
FP64
1.51 TFLOPS
-
|
|
BF16
96.77 TFLOPS
193.54 TFLOPS Tensor
387.07 TFLOPS Tensor Sparse
|
|
TF32
96.77 TFLOPS Tensor
193.54 TFLOPS Tensor Sparse
|
|
INT4
1.55 POPS Tensor
3.1 POPS Tensor Sparse
|
|
INT8
-
774.14 TOPS Tensor
1.55 POPS Tensor Sparse
|
|
INT32
48.38 TOPS
|
|
Ray Tracing
223.7 TOPS
|
|
Pixel Fillrate
462 GPixel/s
|
|
-
-
|
|
Texture Fillrate
1512 GTexel/s
|
|
-
-
|
|
L1
64KB/SM Tex
128KB/SM
-
-
|
|
L2
96MB Shared
|
|
-
-
-
|
|
48GB
GDDR6X
-
|
|
Bus Width
384Bit
|
|
Clock
1313MHz
Transfer Rate
21GT/s
Bandwidth
1008GB/s
|
|
-
-
-
-
-
-
-
-
-
|
|
TDP
600W
|
|
Temp
90°C Max
|
|
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
3x DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
1x HDMI 2.1
-
-
|
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
G-Sync
FreeSync
-
|
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
4
|
|
Content Protection
HDCP 2.3
|
|
Model
2x NVENC 8
|
|
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
Model
NVDEC 5
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
|
|
Direct X
12
Direct 3D
12_3
|
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
|
|
Shader Model
6.6
CUDA
8.9
-
-
PureVideo HD
VP12
VDPAU
Feature Set L
|
|
-
-
-
2x Fans
|
|
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
|
|
Slots Required
3.0
PCIe Version
4.0
PCIe Lanes
16
|
|
-
-
-
-
|
|
Height
137 mm (5.39 in)
Width
304 mm (11.97 in)
Depth
61 mm (2.4 in)
|
Copy Link