GPU Comparison
GEFORCE
NVIDIA GB10
CORE STATE
GB20B
VRAM
128 GB
CLOCK SPEED
2418 MHz
TDP
140 W
BUS WIDTH
256 bit
ARCHITECTURE
Blackwell 2.0
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
Analysis: NVIDIA GB10 vs NVIDIA L4
Looking at the test figures for the NVIDIA NVIDIA L4 and NVIDIA GB10 from NVIDIA, a picture of competitive capability appears. None of the option wins steadily throughout every benchmarks. This alternating of wins implies core balance. Users encounter a real selection between them. Each options provide solid gaming capability.
When those torn between the NVIDIA NVIDIA L4 and NVIDIA GB10 from NVIDIA, remain assured that both choice achieves similar graphics throughput. This test results validates nil definite leader. Form your selection on alternative factors and experience excellent rendering capability no matter what. Each are champions in this respective right. Select confidently.
DETAILED SPECIFICATIONS
SPECIFICATION
GB10
L4
Core Specs
Shading Units
6,144
7,424
+20.8%
Shaders
6,144
7,424
+20.8%
TMUs
384
240
-37.5%
ROPs
48
80
+66.7%
SM Count
48
60
+25.0%
Clocks
Base Clock
1665 MHz
795 MHz
Boost Clock
2418 MHz
2040 MHz
Memory Clock
1067 MHz
8.5 Gbps effective
1563 MHz
12.5 Gbps effective
Memory
Memory Size
128 GB
24 GB
VRAM (MB)
131,072
24,576
-81.3%
Memory Type
LPDDR5X
GDDR6
Memory Bus
256 bit
192 bit
Bandwidth
273.2 GB/s
300.1 GB/s
Cache
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
48 MB
Performance
Pixel Rate
116.1 GPixel/s
163.2 GPixel/s
Texture Rate
928.5 GTexel/s
489.6 GTexel/s
FP32 (TFLOPS)
29.71 TFLOPS
30.29 TFLOPS
FP64 (TFLOPS)
464.3 GFLOPS (1:64)
473.3 GFLOPS (1:64)
FP16 (TFLOPS)
29.71 TFLOPS (1:1)
30.29 TFLOPS (1:1)
AI/RT
RT Cores
48
60
+25.0%
Tensor Cores
384
240
-37.5%
Power
TDP
140 W
72 W
TDP (W)
140
72
-48.6%
Suggested PSU
300 W
250 W
Power Connectors
None
None
Architecture
Architecture
Blackwell 2.0
Ada Lovelace
GPU Name
GB20B
AD104
Generation
Server Blackwell
(Bxx)
Server Ada
(Lxx)
Process Size
5 nm
5 nm
Transistors
—
35,800 million
Die Size
—
294 mm²
Foundry
TSMC
TSMC
Density
—
121.8M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
12.1
8.9
Shader Model
—
6.8
Physical
Slot Width
IGP
Single-slot
Length
150 mm
5.9 inches
169 mm
6.7 inches
Height
51 mm
2 inches
56 mm
2.2 inches
Outputs
1x HDMI
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Other
Launch Price
3,999 USD
—
Production
Active
Active
Predecessor
Server Hopper
Server Ampere
Successor
Server Rubin
Server Hopper