NVIDIA RTX 4000 Ada vs NVIDIA Quadro M3000 SE

NVIDIA RTX 4000 Ada
NVIDIA Quadro M3000 SE
6144 Shaders
20GB GDDR6
2175MHz
1024 Shaders
8GB GDDR5
924MHz
Peak AI Performance
855.24 TOPS
INT4 Tensor Sparse
Peak AI Performance
7.57 TOPS
INT8
FP32
26.73 TFLOPS
FP32
1.89 TFLOPS
FP16
26.73 TFLOPS
-
-
Form Factor
PCIe Card
1.0-Slots
Form Factor
MXM-A
-
TDP
130W
TDP
75W
Power Connectors
-
-
-
1x 16-Pin 12VHPWR
-
-
-
-
-
GB6 OpenCL N/A
0%
GB6 Metal N/A
0%
GB6 Metal N/A
0%
GB6 Vulkan N/A
0%
GB5 OpenCL N/A
0%
GB5 OpenCL N/A
0%
GB5 CUDA N/A
0%
GB5 CUDA N/A
0%
GB5 Metal N/A
0%
GB5 Metal N/A
0%
GB5 Vulkan N/A
0%
GB5 Vulkan N/A
0%
OCT 2020.1 N/A
0%
OCT 2020.1 N/A
0%
OCT Metal N/A
0%
OCT Metal N/A
0%
Peak AI Performance
855.24 TOPS
INT4 Tensor Sparse
Peak AI Performance
7.57 TOPS
INT8
-
-
-
-
-
-
FP8
-
213.81 TFLOPS Tensor (FP16 Accumulate)
427.62 TFLOPS Tensor (FP16 Accumulate) Sparse
213.81 TFLOPS Tensor (FP32 Accumulate)
427.62 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP16
26.73 TFLOPS
106.91 TFLOPS Tensor (FP16 Accumulate)
213.81 TFLOPS Tensor (FP16 Accumulate) Sparse
106.91 TFLOPS Tensor (FP32 Accumulate)
213.81 TFLOPS Tensor (FP32 Accumulate) Sparse
-
-
-
-
-
-
FP32
26.73 TFLOPS
-
-
FP32
1.89 TFLOPS
-
-
FP64
420 GFLOPS
-
FP64
60 GFLOPS
-
BF16
26.73 TFLOPS
106.91 TFLOPS Tensor
213.81 TFLOPS Tensor Sparse
-
-
-
-
TF32
53.45 TFLOPS Tensor
106.91 TFLOPS Tensor Sparse
-
-
-
INT4
427.62 TOPS Tensor
855.24 TOPS Tensor Sparse
-
-
-
INT8
-
213.81 TOPS Tensor
427.62 TOPS Tensor Sparse
INT8
7.57 TOPS
-
-
INT32
13.36 TOPS
INT32
1.89 TOPS
Ray Tracing
61.8 TOPS
-
-
Pixel Fillrate
174 GPixel/s
Pixel Fillrate
29.568 GPixel/s
-
-
-
-
Texture Fillrate
417.6 GTexel/s
Texture Fillrate
59.136 GTexel/s
Manufacturer
NVIDIA
Manufacturer
NVIDIA
Chip Designer
NVIDIA
Chip Designer
NVIDIA
Architecture
Ada Lovelace
Architecture
Maxwell 2
Family
RTX Ada
Family
Quadro M
Codename
NV184
AD104
-
-
Codename
NV124
GM204
Variant
GM204-850-A1
Market Segment
Workstation
Market Segment
Workstation
Release Date
8/9/2023
Release Date
10/2/2016
Foundry
TSMC
-
Foundry
TSMC
-
Fabrication Node
4N
-
Fabrication Node
28nm
-
Die Size
295 mm²
-
Die Size
398 mm²
-
Transistor Count
35.8 Billion
-
Transistor Count
5.2 Billion
-
Transistor Density
121.56M/mm²
-
Transistor Density
13.07M/mm²
-
Form
PCIe Card
Form
MXM-A
Shading Units
6144 Shaders
-
Shading Units
1024 Shaders
-
Texture Mapping Units
192 TMUs
Texture Mapping Units
64 TMUs
Render Output Units
80 ROPs
Render Output Units
32 ROPs
Tensor Cores
192 T-Cores
-
-
Ray-Tracing Cores
48 RT-Cores
-
-
Streaming Multiprocessors
48 SMs
Streaming Multiprocessors
8 SMs
-
-
-
-
-
-
-
-
-
-
-
-
-
-
1500MHz Base
2175MHz
-
-
823MHz Base
924MHz
-
-
-
-
L1
64KB/SM Tex
128KB/SM
-
-
L1
-
48KB/SM
-
-
L2
48MB Shared
L2
2MB Shared
-
-
-
-
-
-
20GB
GDDR6
ECC
8GB
GDDR5
-
Bus Width
160Bit
Bus Width
256Bit
Clock
1750MHz
Transfer Rate
14GT/s
Bandwidth
280GB/s
Clock
1503MHz
Transfer Rate
6GT/s
Bandwidth
192.4GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
130W
TDP
75W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
4x mini-DisplayPort 1.4
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
7680x4320
Max Resolution
4096x2304
Max Resolution Refresh Rate
120Hz
Max Resolution Refresh Rate
60Hz
Variable Refresh Rate
G-Sync
FreeSync
-
Variable Refresh Rate
G-Sync
FreeSync
-
Display Stream Compression (DSC)
Supported
Display Stream Compression (DSC)
Not Supported
Multi Monitor Support
4
Multi Monitor Support
3
Content Protection
HDCP 2.3
-
-
Model
2x NVENC 8
Model
2x NVENC 3
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
-
-
-
Model
2x NVDEC 5
Model
NVDEC 1
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
VP8
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
Codec
MPEG-1
MPEG-2
MPEG-4
-
VC-1
-
-
-
AVC (H.264)
-
-
-
-
-
Direct X
12
Direct 3D
12_3
Direct X
12
Direct 3D
12_1
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
Shader Model
6.7
CUDA
8.9
-
-
PureVideo HD
VP12
VDPAU
Feature Set L
Shader Model
6.7
CUDA
5.2
-
-
PureVideo HD
VP6
VDPAU
Feature Set E
-
-
-
-
Not a Card
-
-
-
Power Connectors
-
-
-
-
-
-
1x 16-Pin 12VHPWR
-
-
-
-
-
-
-
-
Slots Required
1.0
PCIe Version
4.0
PCIe Lanes
16
-
-
PCIe Version
3.0
PCIe Lanes
16
-
-
-
-
-
-
-
-
Height
112 mm (4.41 in)
Width
245 mm (9.65 in)
Depth
20 mm (0.79 in)
-
-
-
-
-
-
Change Comparison