GPU Comparison

NVIDIA
GEFORCE

NVIDIA GB10

CORE STATE GB20B
VRAM 128 GB
CLOCK SPEED 2418 MHz
TDP 140 W
BUS WIDTH 256 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

Tesla P4

CORE STATE GP104
VRAM 8 GB
CLOCK SPEED 1114 MHz
TDP 75 W
BUS WIDTH 256 bit
ARCHITECTURE Pascal
nm
PROCESS 16 nm
LAUNCH DATE 2016

PERFORMANCE BENCHMARKS

geekbench_opencl
120,027
37,896
geekbench_vulkan
114,648
40,309

DETAILED SPECIFICATIONS

SPECIFICATION
GB10
Tesla P4
Core Specs
Shading Units
6,144
2,560 -58.3%
Shaders
6,144
2,560 -58.3%
TMUs
384
160 -58.3%
ROPs
48
64 +33.3%
SM Count
48
20 -58.3%
Clocks
Base Clock
1665 MHz
886 MHz
Boost Clock
2418 MHz
1114 MHz
Memory Clock
1067 MHz 8.5 Gbps effective
1502 MHz 6 Gbps effective
Memory
Memory Size
128 GB
8 GB
VRAM (MB)
131,072
8,192 -93.8%
Memory Type
LPDDR5X
GDDR5
Memory Bus
256 bit
256 bit
Bandwidth
273.2 GB/s
192.3 GB/s
Cache
L1 Cache
256 KB (per SM)
48 KB (per SM)
L2 Cache
50 MB
2 MB
Performance
Pixel Rate
116.1 GPixel/s
71.30 GPixel/s
Texture Rate
928.5 GTexel/s
178.2 GTexel/s
FP32 (TFLOPS)
29.71 TFLOPS
5.704 TFLOPS
FP64 (TFLOPS)
464.3 GFLOPS (1:64)
178.2 GFLOPS (1:32)
FP16 (TFLOPS)
29.71 TFLOPS (1:1)
89.12 GFLOPS (1:64)
AI/RT
RT Cores
48
Tensor Cores
384
Power
TDP
140 W
75 W
TDP (W)
140
75 -46.4%
Suggested PSU
300 W
250 W
Power Connectors
None
None
Architecture
Architecture
Blackwell 2.0
Pascal
GPU Name
GB20B
GP104
Generation
Server Blackwell (Bxx)
Tesla Pascal (Pxx)
Process Size
5 nm
16 nm
Transistors
7,200 million
Die Size
314 mm²
Foundry
TSMC
TSMC
Density
22.9M / mm²
API Support
DirectX
12 (12_1)
OpenGL
4.6
Vulkan
1.4
OpenCL
3.0
3.0
CUDA
12.1
6.1
Shader Model
6.8
Physical
Slot Width
IGP
Single-slot
Length
150 mm 5.9 inches
168 mm 6.6 inches
Height
51 mm 2 inches
Outputs
1x HDMI
No outputs
Bus Interface
PCIe 5.0 x16
PCIe 3.0 x16
Other
Launch Price
3,999 USD
Production
Active
End-of-life
Predecessor
Server Hopper
Tesla Maxwell
Successor
Server Rubin
Tesla Volta
View GB10 Details View Tesla P4 Details