GPU Comparison
GEFORCE
NVIDIA B300 SXM6 AC
CORE STATE
GB110
VRAM
288 GB
CLOCK SPEED
2032 MHz
TDP
1100 W
BUS WIDTH
8192 bit
ARCHITECTURE
Blackwell Ultra
PROCESS
5 nm
LAUNCH DATE
2025
VS
GEFORCE
L4
CORE STATE
AD104
VRAM
24 GB
CLOCK SPEED
2040 MHz
TDP
72 W
BUS WIDTH
192 bit
ARCHITECTURE
Ada Lovelace
PROCESS
5 nm
LAUNCH DATE
2023
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
DETAILED SPECIFICATIONS
SPECIFICATION
B300 SXM6 AC
L4
Core Specs
Shading Units
18,944
7,424
-60.8%
Shaders
18,944
7,424
-60.8%
TMUs
592
240
-59.5%
ROPs
24
80
+233.3%
SM Count
148
60
-59.5%
Clocks
Base Clock
1665 MHz
795 MHz
Boost Clock
2032 MHz
2040 MHz
Memory Clock
2000 MHz 8 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
288 GB
24 GB
VRAM (MB)
294,912
24,576
-91.7%
Memory Type
HBM3e
GDDR6
Memory Bus
8192 bit
192 bit
Bandwidth
8.19 TB/s
300.1 GB/s
Cache
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
126 MB
48 MB
Performance
Pixel Rate
48.77 GPixel/s
163.2 GPixel/s
Texture Rate
1,202.9 GTexel/s
489.6 GTexel/s
FP32 (TFLOPS)
76.99 TFLOPS
30.29 TFLOPS
FP64 (TFLOPS)
1,202.9 GFLOPS (1:64)
473.3 GFLOPS (1:64)
FP16 (TFLOPS)
76.99 TFLOPS (1:1)
30.29 TFLOPS (1:1)
AI/RT
RT Cores
—
60
Tensor Cores
592
240
-59.5%
Power
TDP
1100 W
72 W
TDP (W)
1,100
72
-93.5%
Suggested PSU
1500 W
250 W
Power Connectors
—
None
Architecture
Architecture
Blackwell Ultra
Ada Lovelace
GPU Name
GB110
AD104
Generation
Server Blackwell (Bxx)
Server Ada
(Lxx)
Process Size
5 nm
5 nm
Transistors
208,000 million
35,800 million
Die Size
1628 mm²
294 mm²
Foundry
TSMC
TSMC
Density
127.8M / mm²
121.8M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
10.3
8.9
Shader Model
—
6.8
Physical
Slot Width
SXM Module
Single-slot
Length
—
169 mm
6.7 inches
Height
—
56 mm
2.2 inches
Outputs
No outputs
No outputs
Bus Interface
PCIe 6.0 x16
PCIe 4.0 x16
Other
Production
Active
Active
Predecessor
Server Hopper
Server Ampere
Successor
Server Rubin
Server Hopper