GPU Comparison
RADEON
AMD Radeon RX 9070
CORE STATE
Navi 48
VRAM
16 GB
CLOCK SPEED
2520 MHz
TDP
220 W
BUS WIDTH
256 bit
ARCHITECTURE
RDNA 4.0
PROCESS
4 nm
LAUNCH DATE
2025
VS
GEFORCE
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
PERFORMANCE BENCHMARKS
3dmark_3dmark_steel_nomad_dx12
geekbench_opencl
geekbench_vulkan
passmark_directx_10
passmark_directx_11
passmark_directx_12
passmark_directx_9
passmark_g2d
passmark_g3d
passmark_gpu_compute
Analysis: AMD Radeon RX 9070 vs NVIDIA GB10
RX 9070 (AMD) and the NVIDIA GB10 card from NVIDIA deliver almost equal gaming results in our side-by-side analysis. Any benchmark deltas between the cards typically land inside margin of error, leaving either a valid selection. This balance renders the determination interesting. Secondary elements become particularly significant. Value usually sways the decision.
When users torn between RX 9070 (AMD) and the NVIDIA GB10 card from NVIDIA, remain certain that any option provides matching gaming capability. The performance figures confirms no decisive leader. Form your decision on other factors and appreciate excellent gaming capability in any case. The two are winners in their own regard. Pick safely.
DETAILED SPECIFICATIONS
SPECIFICATION
RX 9070
GB10
Core Specs
Shading Units
3,584
6,144
+71.4%
Shaders
3,584
6,144
+71.4%
TMUs
224
384
+71.4%
ROPs
128
48
-62.5%
Compute Units
56
—
SM Count
—
48
Clocks
Base Clock
1330 MHz
1665 MHz
Boost Clock
2520 MHz
2418 MHz
Game Clock
2070 MHz
—
Memory Clock
2518 MHz
20.1 Gbps effective
1067 MHz
8.5 Gbps effective
Memory
Memory Size
16 GB
128 GB
VRAM (MB)
16,384
131,072
+700.0%
Memory Type
GDDR6
LPDDR5X
Memory Bus
256 bit
256 bit
Bandwidth
644.6 GB/s
273.2 GB/s
Cache
L1 Cache
—
256 KB (per SM)
L2 Cache
8 MB
50 MB
L3 Cache
64 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
322.6 GPixel/s
116.1 GPixel/s
Texture Rate
564.5 GTexel/s
928.5 GTexel/s
FP32 (TFLOPS)
36.13 TFLOPS
29.71 TFLOPS
FP64 (TFLOPS)
1,129.0 GFLOPS (1:32)
464.3 GFLOPS (1:64)
FP16 (TFLOPS)
72.25 TFLOPS (2:1)
29.71 TFLOPS (1:1)
AI/RT
RT Cores
56
48
-14.3%
Tensor Cores
—
384
Matrix Cores
112
—
Power
TDP
220 W
140 W
TDP (W)
220
140
-36.4%
Suggested PSU
550 W
300 W
Power Connectors
2x 8-pin
None
Architecture
Architecture
RDNA 4.0
Blackwell 2.0
GPU Name
Navi 48
GB20B
Generation
Navi IV
(RX 9000)
Server Blackwell
(Bxx)
Process Size
4 nm
5 nm
Transistors
53,900 million
—
Die Size
357 mm²
—
Foundry
TSMC
TSMC
Density
151.0M / mm²
—
API Support
DirectX
12 Ultimate (12_2)
—
OpenGL
4.6
—
Vulkan
1.4
—
OpenCL
2.2
3.0
CUDA
—
12.1
Shader Model
6.8
—
Physical
Slot Width
Dual-slot
IGP
Length
—
150 mm
5.9 inches
Height
—
51 mm
2 inches
Outputs
1x HDMI 2.1b3x DisplayPort 2.1a
1x HDMI
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Other
Launch Price
549 USD
3,999 USD
Production
Active
Active
Predecessor
Navi III
Server Hopper
Successor
—
Server Rubin