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
Quadro K4000
CORE STATE
GK106
VRAM
3 GB
CLOCK SPEED
—
TDP
80 W
BUS WIDTH
192 bit
ARCHITECTURE
Kepler
PROCESS
28 nm
LAUNCH DATE
2013
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
geekbench_metal
DETAILED SPECIFICATIONS
SPECIFICATION
GB10
Quadro K4000
Core Specs
Shading Units
6,144
768
-87.5%
Shaders
6,144
768
-87.5%
TMUs
384
64
-83.3%
ROPs
48
24
-50.0%
SM Count
48
—
Clocks
Base Clock
1665 MHz
—
Boost Clock
2418 MHz
—
GPU Clock
—
810 MHz
Memory Clock
1067 MHz
8.5 Gbps effective
1404 MHz
5.6 Gbps effective
Memory
Memory Size
128 GB
3 GB
VRAM (MB)
131,072
3,072
-97.7%
Memory Type
LPDDR5X
GDDR5
Memory Bus
256 bit
192 bit
Bandwidth
273.2 GB/s
134.8 GB/s
Cache
L1 Cache
256 KB (per SM)
16 KB (per SMX)
L2 Cache
50 MB
384 KB
Performance
Pixel Rate
116.1 GPixel/s
12.96 GPixel/s
Texture Rate
928.5 GTexel/s
51.84 GTexel/s
FP32 (TFLOPS)
29.71 TFLOPS
1,244.2 GFLOPS
FP64 (TFLOPS)
464.3 GFLOPS (1:64)
51.84 GFLOPS (1:24)
FP16 (TFLOPS)
29.71 TFLOPS (1:1)
—
AI/RT
RT Cores
48
—
Tensor Cores
384
—
Power
TDP
140 W
80 W
TDP (W)
140
80
-42.9%
Suggested PSU
300 W
250 W
Power Connectors
None
1x 6-pin
Architecture
Architecture
Blackwell 2.0
Kepler
GPU Name
GB20B
GK106
Generation
Server Blackwell
(Bxx)
Quadro Kepler
(Kx000)
Process Size
5 nm
28 nm
Transistors
—
2,540 million
Die Size
—
221 mm²
Foundry
TSMC
TSMC
Density
—
11.5M / mm²
API Support
DirectX
—
12 (11_0)
OpenGL
—
4.6
Vulkan
—
1.2.175
OpenCL
3.0
3.0
CUDA
12.1
3.0
Shader Model
—
6.5 (5.1)
Physical
Slot Width
IGP
Single-slot
Length
150 mm
5.9 inches
241 mm
9.5 inches
Height
51 mm
2 inches
111 mm
4.4 inches
Outputs
1x HDMI
1x DVI2x DisplayPort 1.2
Bus Interface
PCIe 5.0 x16
PCIe 2.0 x16
Other
Launch Price
3,999 USD
1,269 USD
Production
Active
End-of-life
Predecessor
Server Hopper
Quadro Fermi
Successor
Server Rubin
Quadro Maxwell