NVIDIA GeForce RTX 3080 12 GB vs NVIDIA RTX PRO 6000 Blackwell
We compared two Desktop platform GPUs: 12GB VRAM GeForce RTX 3080 12 GB and 96GB VRAM RTX PRO 6000 Blackwell to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA GeForce RTX 3080 12 GB 's Advantages
Lower TDP (350W vs 600W)
NVIDIA RTX PRO 6000 Blackwell 's Advantages
Released 3 years and 2 months late
Boost Clock has increased by 53% (2617MHz vs 1710MHz)
More VRAM (96GB vs 12GB)
Larger VRAM bandwidth (1.79TB/s vs 912.4GB/s)
15104 additional rendering cores
Score
Benchmark
FP32 (float)
GeForce RTX 3080 12 GB
30.64 TFLOPS
RTX PRO 6000 Blackwell
+311%
126 TFLOPS
Graphics Card
Jan 2022
Release Date
Mar 2025
GeForce 30
Generation
Blackwell PRO W
Desktop
Type
Desktop
PCIe 4.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1260 MHz
Base Clock
1590 MHz
1710 MHz
Boost Clock
2617 MHz
1188 MHz
Memory Clock
1750 MHz
Memory
12GB
Memory Size
96GB
GDDR6X
Memory Type
GDDR7
384bit
Memory Bus
512bit
912.4GB/s
Bandwidth
1.79TB/s
Render Config
-
-
-
70
SM Count
188
8960
Shading Units
24064
280
TMUs
752
96
ROPs
192
280
Tensor Cores
752
70
RT Cores
188
128 KB (per SM)
L1 Cache
128 KB (per SM)
6 MB
L2 Cache
128 MB
-
-
-
Theoretical Performance
164.2 GPixel/s
Pixel Rate
502.5 GPixel/s
478.8 GTexel/s
Texture Rate
1968 GTexel/s
30.64 TFLOPS
FP16 (half)
126.0 TFLOPS
30.64 TFLOPS
FP32 (float)
126.0 TFLOPS
478.8 GFLOPS
FP64 (double)
1.968 TFLOPS
Board Design
350W
TDP
600W
750 W
Suggested PSU
1000 W
1x HDMI 2.1
3x DisplayPort 1.4a
Outputs
4x DisplayPort 2.1b
1x 12-pin
Power Connectors
1x 16-pin
Graphics Processor
GA102
GPU Name
GB202
GA102-220-A1
GPU Variant
-
Ampere
Architecture
Blackwell 2.0
Samsung
Foundry
TSMC
8 nm
Process Size
5 nm
28.3 billion
Transistors
92.2 billion
628 mm²
Die Size
750 mm²
Graphics Features
12 Ultimate (12_2)
DirectX
12 Ultimate (12_2)
4.6
OpenGL
4.6
3.0
OpenCL
3.0
1.3
Vulkan
1.4
8.6
CUDA
12.0
6.8
Shader Model
6.8
