NVIDIA B200 SXM 192 GB vs NVIDIA GeForce RTX 3060 Ti GDDR6X
We compared two Desktop platform GPUs: 96GB VRAM B200 SXM 192 GB and 8GB VRAM GeForce RTX 3060 Ti GDDR6X to see which GPU has better performance in key specifications, benchmark tests, power consumption, etc.
Main Differences
NVIDIA B200 SXM 192 GB 's Advantages
Released 1 years and 3 months late
Boost Clock has increased by 10% (1837MHz vs 1665MHz)
More VRAM (96GB vs 8GB)
Larger VRAM bandwidth (4.10TB/s vs 608.3GB/s)
12032 additional rendering cores
NVIDIA GeForce RTX 3060 Ti GDDR6X 's Advantages
Lower TDP (225W vs 1000W)
Score
Benchmark
FP32 (float)
B200 SXM 192 GB
+283%
62.08 TFLOPS
GeForce RTX 3060 Ti GDDR6X
16.2 TFLOPS
Graphics Card
Jan 2024
Release Date
Oct 2022
Server Blackwell
Generation
GeForce 30
Desktop
Type
Desktop
PCIe 5.0 x16
Bus Interface
PCIe 4.0 x16
Clock Speeds
1665 MHz
Base Clock
1410 MHz
1837 MHz
Boost Clock
1665 MHz
2000 MHz
Memory Clock
1188 MHz
Memory
96GB
Memory Size
8GB
HBM3e
Memory Type
GDDR6X
4096bit
Memory Bus
256bit
4.10TB/s
Bandwidth
608.3GB/s
Render Config
-
-
-
132
SM Count
38
16896
Shading Units
4864
528
TMUs
152
24
ROPs
80
528
Tensor Cores
152
-
RT Cores
38
256 KB (per SM)
L1 Cache
128 KB (per SM)
50 MB
L2 Cache
4 MB
-
-
-
Theoretical Performance
44.09 GPixel/s
Pixel Rate
133.2 GPixel/s
969.9 GTexel/s
Texture Rate
253.1 GTexel/s
248.3 TFLOPS
FP16 (half)
16.20 TFLOPS
62.08 TFLOPS
FP32 (float)
16.20 TFLOPS
31.04 TFLOPS
FP64 (double)
253.1 GFLOPS
Board Design
1000W
TDP
225W
1400 W
Suggested PSU
550 W
No outputs
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
-
Power Connectors
1x 12-pin
Graphics Processor
GB100
GPU Name
GA104
-
GPU Variant
GA104-202-A1
Blackwell
Architecture
Ampere
TSMC
Foundry
Samsung
5 nm
Process Size
8 nm
104 billion
Transistors
17.4 billion
Unknown
Die Size
392 mm²
Graphics Features
N/A
DirectX
12 Ultimate (12_2)
N/A
OpenGL
4.6
3.0
OpenCL
3.0
N/A
Vulkan
1.3
10.0
CUDA
8.6
N/A
Shader Model
6.7
