GPU Comparison
GEFORCE
NVIDIA P104-100
CORE STATE
GP104
VRAM
4 GB
CLOCK SPEED
1733 MHz
TDP
—
BUS WIDTH
256 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
VS
GEFORCE
RTX 5000 Ada Generation
CORE STATE
AD102
VRAM
32 GB
CLOCK SPEED
2550 MHz
TDP
250 W
BUS WIDTH
256 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
P104-100
RTX 5000 Ada Generation
Core Specs
Shading Units
1,920
12,800
+566.7%
Shaders
1,920
12,800
+566.7%
TMUs
120
400
+233.3%
ROPs
64
176
+175.0%
SM Count
15
100
+566.7%
Clocks
Base Clock
1607 MHz
1155 MHz
Boost Clock
1733 MHz
2550 MHz
Memory Clock
1251 MHz
10 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
4 GB
32 GB
VRAM (MB)
4,096
32,768
+700.0%
Memory Type
GDDR5X
GDDR6
Memory Bus
256 bit
256 bit
Bandwidth
320.3 GB/s
576.0 GB/s
Cache
L1 Cache
48 KB (per SM)
128 KB (per SM)
L2 Cache
2 MB
72 MB
Performance
Pixel Rate
110.9 GPixel/s
448.8 GPixel/s
Texture Rate
208.0 GTexel/s
1,020.0 GTexel/s
FP32 (TFLOPS)
6.655 TFLOPS
65.28 TFLOPS
FP64 (TFLOPS)
208.0 GFLOPS (1:32)
1,020.0 GFLOPS (1:64)
FP16 (TFLOPS)
104.0 GFLOPS (1:64)
65.28 TFLOPS (1:1)
AI/RT
RT Cores
—
100
Tensor Cores
—
400
Power
TDP
—
250 W
TDP (W)
—
250
Suggested PSU
200 W
600 W
Power Connectors
1x 8-pin
1x 16-pin
Architecture
Architecture
Pascal
Ada Lovelace
GPU Name
GP104
AD102
Generation
Mining GPUs
Workstation Ada
(x000A)
Process Size
16 nm
5 nm
Transistors
7,200 million
76,300 million
Die Size
314 mm²
609 mm²
Foundry
TSMC
TSMC
Density
22.9M / mm²
125.3M / mm²
API Support
DirectX
12 (12_1)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
3.0
3.0
CUDA
6.1
8.9
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Dual-slot
Length
267 mm
10.5 inches
267 mm
10.5 inches
Height
—
112 mm
4.4 inches
Outputs
No outputs
4x DisplayPort 1.4a
Bus Interface
PCIe 1.0 x4
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Workstation Ampere
Successor
—
Blackwell PRO W