GPU Comparison
RADEON
AMD Radeon Pro W6600X
CORE STATE
Navi 23
VRAM
8 GB
CLOCK SPEED
2479 MHz
TDP
120 W
BUS WIDTH
128 bit
ARCHITECTURE
RDNA 2.0
PROCESS
7 nm
LAUNCH DATE
2021
VS
GEFORCE
GeForce RTX 3090 Ti
CORE STATE
GA102
VRAM
24 GB
CLOCK SPEED
1860 MHz
TDP
450 W
BUS WIDTH
384 bit
ARCHITECTURE
Ampere
PROCESS
8 nm
LAUNCH DATE
2022
PERFORMANCE BENCHMARKS
geekbench_metal
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
Pro W6600X
RTX 3090 Ti
Core Specs
Shading Units
2,048
10,752
+425.0%
Shaders
2,048
10,752
+425.0%
TMUs
128
336
+162.5%
ROPs
64
112
+75.0%
Compute Units
32
—
SM Count
—
84
Clocks
Base Clock
2068 MHz
1560 MHz
Boost Clock
2479 MHz
1860 MHz
Memory Clock
2000 MHz
16 Gbps effective
1313 MHz
21 Gbps effective
Memory
Memory Size
8 GB
24 GB
VRAM (MB)
8,192
24,576
+200.0%
Memory Type
GDDR6
GDDR6X
Memory Bus
128 bit
384 bit
Bandwidth
256.0 GB/s
1.01 TB/s
Cache
L1 Cache
128 KB per Array
128 KB (per SM)
L2 Cache
2 MB
6 MB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
158.7 GPixel/s
208.3 GPixel/s
Texture Rate
317.3 GTexel/s
625.0 GTexel/s
FP32 (TFLOPS)
10.15 TFLOPS
40.00 TFLOPS
FP64 (TFLOPS)
634.6 GFLOPS (1:16)
625.0 GFLOPS (1:64)
FP16 (TFLOPS)
20.31 TFLOPS (2:1)
40.00 TFLOPS (1:1)
AI/RT
RT Cores
32
84
+162.5%
Tensor Cores
—
336
Power
TDP
120 W
450 W
TDP (W)
120
450
+275.0%
Suggested PSU
300 W
850 W
Power Connectors
—
1x 16-pin
Architecture
Architecture
RDNA 2.0
Ampere
GPU Name
Navi 23
GA102
Generation
Radeon Pro Mac
(Navi II Series)
GeForce 30
Process Size
7 nm
8 nm
Transistors
11,060 million
28,300 million
Die Size
237 mm²
628 mm²
Foundry
TSMC
Samsung
Density
46.7M / mm²
45.1M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.1
3.0
CUDA
—
8.6
Shader Model
6.8
6.8
Physical
Slot Width
Dual-slot
Triple-slot
Length
—
336 mm
13.2 inches
Height
—
140 mm
5.5 inches
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
Apple MPX
PCIe 4.0 x16
Other
Launch Price
699 USD
1,999 USD
Production
End-of-life
End-of-life
Predecessor
—
GeForce 20
Successor
—
GeForce 40