NVIDIA B100 vs AMD Radeon RX 9070 XT
We compared two Desktop platform GPUs: 96GB VRAM B100 and 16GB VRAM Radeon RX 9070 XT to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B100 's Advantages
More VRAM (96GB vs 16GB)
Larger VRAM bandwidth (4.10TB/s vs 644.6GB/s)
12800 additional rendering cores
AMD Radeon RX 9070 XT 's Advantages
Boost Clock has increased by 62% (2970MHz vs 1837MHz)
Lower TDP (304W vs 1000W)
Score
Benchmark
FP32 (float)
B100
+27%
62.08 TFLOPS
Radeon RX 9070 XT
48.66 TFLOPS
Graphics Card
Nov 2024
Release Date
Mar 2025
Server Blackwell
Generation
Navi IV
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 5.0 x16
Clock Speeds
1665 MHz
Base Clock
1660 MHz
1837 MHz
Boost Clock
2970 MHz
2000 MHz
Memory Clock
2518 MHz
Memory
96GB
Memory Size
16GB
HBM3e
Memory Type
GDDR6
4096bit
Memory Bus
256bit
4.10TB/s
Bandwidth
644.6GB/s
Render Config
-
Compute Units
64
132
SM Count
-
16896
Shading Units
4096
528
TMUs
256
24
ROPs
128
528
Tensor Cores
128
-
RT Cores
64
256 KB (per SM)
L1 Cache
128 KB per Array
50 MB
L2 Cache
8 MB
-
L3 Cache
64 MB
Theoretical Performance
44.09 GPixel/s
Pixel Rate
380.2 GPixel/s
969.9 GTexel/s
Texture Rate
760.3 GTexel/s
248.3 TFLOPS
FP16 (half)
97.32 TFLOPS
62.08 TFLOPS
FP32 (float)
48.66 TFLOPS
31.04 TFLOPS
FP64 (double)
1.521 TFLOPS
Board Design
1000W
TDP
304W
1400 W
Suggested PSU
700 W
No outputs
Outputs
1x HDMI 2.1b
3x DisplayPort 2.1a
-
Power Connectors
2x 8-pin
Graphics Processor
GB102
GPU Name
Navi 48
-
GPU Variant
Navi 48 XT
(215-176600315)
Blackwell
Architecture
RDNA 4.0
TSMC
Foundry
TSMC
5 nm
Process Size
5 nm
104 billion
Transistors
53.9 billion
Unknown
Die Size
357 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
2.2
N/A
Vulkan
1.3
10.1
CUDA
-
N/A
Shader Model
6.8
