NVIDIA B300 SXM6 AC vs NVIDIA RTX PRO 4000 Blackwell

GPU · Specs Compare

Products
GPU NVIDIA B300 SXM6 AC NVIDIA · 2025-09
GPU NVIDIA RTX PRO 4000 Blackwell NVIDIA · 2025-03
Graphics Card
Release Date
Sep 2025
Mar 2025
Generation
Server Blackwell
Blackwell PRO W
Type
Desktop
Desktop
Bus Interface
PCIe 6.0 x16
PCIe 5.0 x16
Clock Speeds
Base Clock
1665 MHz
1230 MHz
Boost Clock
2032 MHz
2055 MHz
Memory Clock
2000 MHz
1750 MHz
Memory
Memory Size
288GB
24GB
Memory Type
HBM3e
GDDR7
Memory Bus
8192bit
192bit
Bandwidth
8.19TB/s
672.0GB/s
Render Config
SM Count
148
70
Shading Units
18944
8960
TMUs
592
280
ROPs
24
96
Tensor Cores
592
280
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
126 MB
48 MB
RT Cores
—
70
Theoretical Performance
Pixel Rate
48.77 GPixel/s
197.3 GPixel/s
Texture Rate
1202.9 GTexel/s
575.4 GTexel/s
FP16 (half)
76.99 TFLOPS
36.83 TFLOPS
FP32 (float)
76.99 TFLOPS
36.83 TFLOPS
FP64 (double)
1202.9 GFLOPS
575.4 GFLOPS
Graphics Processor
GPU Name
GB110
GB203
Architecture
Blackwell Ultra
Blackwell 2.0
Foundry
TSMC
TSMC
Process Size
5 nm
5 nm
Transistors
208 billion
45.6 billion
Die Size
1628 mm²
378 mm²
Board Design
TDP
1100W
140W
Suggested PSU
1500 W
300 W
Outputs
No outputs
4x DisplayPort 2.1b
Power Connectors
—
1x 16-pin
Graphics Features
DirectX
N/A
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
3.0
3.0
Vulkan
N/A
1.4
CUDA
10.3
12.0
Shader Model
N/A
6.8
▲ Specs Compare Data sourced from official specifications and benchmark tests.