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
GeForce RTX 5080
CORE STATE
GB203
VRAM
16 GB
CLOCK SPEED
2617 MHz
TDP
360 W
BUS WIDTH
256 bit
ARCHITECTURE
Blackwell 2.0
PROCESS
5 nm
LAUNCH DATE
2025
PERFORMANCE BENCHMARKS
geekbench_opencl
geekbench_vulkan
3dmark_3dmark_steel_nomad_dx12
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
Analysis: NVIDIA GB10 vs NVIDIA GeForce RTX 5080
NVIDIA's RTX 5080 and NVIDIA GB10 from NVIDIA deliver almost equal rendering performance in our side-by-side evaluation. Any benchmark deltas between both GPUs typically sit below 5-10%, making each a good option. The parity makes the determination interesting. Alternative variables get particularly important. Price typically sways the choice.
For users uncertain between NVIDIA's RTX 5080 and NVIDIA GB10 from NVIDIA, rest certain that either selection achieves equivalent graphics results. The test data confirms nil clear winner. Make your determination on other variables and experience excellent visual results in any case. Either are capable in their own sense. Pick assuredly.
DETAILED SPECIFICATIONS
SPECIFICATION
GB10
RTX 5080
Core Specs
Shading Units
6,144
10,752
+75.0%
Shaders
6,144
10,752
+75.0%
TMUs
384
336
-12.5%
ROPs
48
112
+133.3%
SM Count
48
84
+75.0%
Clocks
Base Clock
1665 MHz
2295 MHz
Boost Clock
2418 MHz
2617 MHz
Memory Clock
1067 MHz
8.5 Gbps effective
1875 MHz
30 Gbps effective
Memory
Memory Size
128 GB
16 GB
VRAM (MB)
131,072
16,384
-87.5%
Memory Type
LPDDR5X
GDDR7
Memory Bus
256 bit
256 bit
Bandwidth
273.2 GB/s
960.0 GB/s
Cache
L1 Cache
256 KB (per SM)
128 KB (per SM)
L2 Cache
50 MB
64 MB
Performance
Pixel Rate
116.1 GPixel/s
293.1 GPixel/s
Texture Rate
928.5 GTexel/s
879.3 GTexel/s
FP32 (TFLOPS)
29.71 TFLOPS
56.28 TFLOPS
FP64 (TFLOPS)
464.3 GFLOPS (1:64)
879.3 GFLOPS (1:64)
FP16 (TFLOPS)
29.71 TFLOPS (1:1)
56.28 TFLOPS (1:1)
AI/RT
RT Cores
48
84
+75.0%
Tensor Cores
384
336
-12.5%
Power
TDP
140 W
360 W
TDP (W)
140
360
+157.1%
Suggested PSU
300 W
750 W
Power Connectors
None
1x 16-pin
Architecture
Architecture
Blackwell 2.0
Blackwell 2.0
GPU Name
GB20B
GB203
Generation
Server Blackwell
(Bxx)
GeForce 50
Process Size
5 nm
5 nm
Transistors
—
45,600 million
Die Size
—
378 mm²
Foundry
TSMC
TSMC
Density
—
120.6M / mm²
API Support
DirectX
—
12 Ultimate (12_2)
OpenGL
—
4.6
Vulkan
—
1.4
OpenCL
3.0
3.0
CUDA
12.1
12.0
Shader Model
—
6.8
Physical
Slot Width
IGP
Dual-slot
Length
150 mm
5.9 inches
304 mm
12 inches
Height
51 mm
2 inches
137 mm
5.4 inches
Outputs
1x HDMI
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Other
Launch Price
3,999 USD
999 USD
Production
Active
Active
Predecessor
Server Hopper
GeForce 40
Successor
Server Rubin
—