GPU Comparison
GEFORCE
NVIDIA P106-090
CORE STATE
GP106
VRAM
3 GB
CLOCK SPEED
1531 MHz
TDP
75 W
BUS WIDTH
192 bit
ARCHITECTURE
Pascal
PROCESS
16 nm
LAUNCH DATE
2017
VS
GEFORCE
RTX 4000 Ada Generation
CORE STATE
AD104
VRAM
20 GB
CLOCK SPEED
2175 MHz
TDP
130 W
BUS WIDTH
160 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
P106-090
RTX 4000 Ada Generation
Core Specs
Shading Units
768
6,144
+700.0%
Shaders
768
6,144
+700.0%
TMUs
48
192
+300.0%
ROPs
48
64
+33.3%
SM Count
6
48
+700.0%
Clocks
Base Clock
1354 MHz
1500 MHz
Boost Clock
1531 MHz
2175 MHz
Memory Clock
2002 MHz
8 Gbps effective
2250 MHz
18 Gbps effective
Memory
Memory Size
3 GB
20 GB
VRAM (MB)
3,072
20,480
+566.7%
Memory Type
GDDR5
GDDR6
Memory Bus
192 bit
160 bit
Bandwidth
192.2 GB/s
360.0 GB/s
Cache
L1 Cache
48 KB (per SM)
128 KB (per SM)
L2 Cache
1536 KB
48 MB
Performance
Pixel Rate
73.49 GPixel/s
139.2 GPixel/s
Texture Rate
73.49 GTexel/s
417.6 GTexel/s
FP32 (TFLOPS)
2.352 TFLOPS
26.73 TFLOPS
FP64 (TFLOPS)
73.49 GFLOPS (1:32)
417.6 GFLOPS (1:64)
FP16 (TFLOPS)
36.74 GFLOPS (1:64)
26.73 TFLOPS (1:1)
AI/RT
RT Cores
—
48
Tensor Cores
—
192
Power
TDP
75 W
130 W
TDP (W)
75
130
+73.3%
Suggested PSU
250 W
300 W
Power Connectors
1x 6-pin
1x 16-pin
Architecture
Architecture
Pascal
Ada Lovelace
GPU Name
GP106
AD104
Generation
Mining GPUs
Workstation Ada
(x000A)
Process Size
16 nm
5 nm
Transistors
4,400 million
35,800 million
Die Size
200 mm²
294 mm²
Foundry
TSMC
TSMC
Density
22.0M / mm²
121.8M / 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
Single-slot
Length
250 mm
9.8 inches
245 mm
9.6 inches
Height
—
112 mm
4.4 inches
Outputs
No outputs
4x DisplayPort 1.4a
Bus Interface
PCIe 1.0 x1
PCIe 4.0 x16
Other
Production
End-of-life
Active
Predecessor
—
Workstation Ampere
Successor
—
Blackwell PRO W