NVIDIA Quadro RTX 8000 vs NVIDIA B300 SXM6 AC
GPU · Specs Compare
Graphics Card
Release Date
Aug 2018
Sep 2025
Generation
Quadro
Server Blackwell
Type
Professional
Desktop
Bus Interface
PCIe 3.0 x16
PCIe 6.0 x16
Clock Speeds
Base Clock
1395 MHz
1665 MHz
Boost Clock
1770 MHz
2032 MHz
Memory Clock
1750 MHz
2000 MHz
Memory
Memory Size
48GB
288GB
Memory Type
GDDR6
HBM3e
Memory Bus
384bit
8192bit
Bandwidth
672.0GB/s
8.19TB/s
Render Config
SM Count
72
148
Shading Units
4608
18944
TMUs
288
592
ROPs
96
24
Tensor Cores
576
592
RT Cores
72
—
L1 Cache
64 KB (per SM)
256 KB (per SM)
L2 Cache
6 MB
126 MB
Theoretical Performance
Pixel Rate
169.9 GPixel/s
48.77 GPixel/s
Texture Rate
509.8 GTexel/s
1202.9 GTexel/s
FP16 (half)
32.62 TFLOPS
76.99 TFLOPS
FP32 (float)
16.31 TFLOPS
76.99 TFLOPS
FP64 (double)
509.8 GFLOPS
1202.9 GFLOPS
Graphics Processor
GPU Name
TU102
GB110
GPU Variant
TU102-875-A1
—
Architecture
Turing
Blackwell Ultra
Foundry
TSMC
TSMC
Process Size
12 nm
5 nm
Transistors
18.6 billion
208 billion
Die Size
754 mm²
1628 mm²
Board Design
TDP
260W
1100W
Suggested PSU
600 W
1500 W
Outputs
4x DisplayPort 1.4a1x USB Type-C
No outputs
Power Connectors
1x 6-pin + 1x 8-pin
—
Graphics Features
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
N/A
OpenCL
3.0
3.0
Vulkan
1.3
N/A
CUDA
7.5
10.3
Shader Model
6.6
N/A
Benchmark
3DMark Time Spy
13,586
—
3DMark Time Spy Extreme
6,871
—
OctaneBench
337
—
3DMark Speed Way
3,121
—
Blender
2,844
—
▲ Specs Compare
Data sourced from official specifications and benchmark tests.