AMD Radeon AI PRO 9600D vs NVIDIA GeForce RTX 5090 Mobile Comparison

AMD
RADEON

AMD Radeon AI PRO 9600D

CORE STATE Navi 48
VRAM 32 GB
CLOCK SPEED 2020 MHz
TDP 150 W
BUS WIDTH 256 bit
ARCHITECTURE RDNA 4.0
nm
PROCESS 4 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

GeForce RTX 5090 Mobile

CORE STATE GB203
VRAM 24 GB
CLOCK SPEED 1515 MHz
TDP 95 W
BUS WIDTH 256 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2025

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
N/A
5,871
geekbench_opencl
N/A
201,834
geekbench_vulkan
N/A
198,405
passmark_directx_10
N/A
183
passmark_directx_11
N/A
269
passmark_directx_12
N/A
138
passmark_directx_9
N/A
324
passmark_g2d
N/A
1,057
passmark_g3d
N/A
30,034
passmark_gpu_compute
N/A
13,401

Analysis: AMD Radeon AI PRO 9600D vs NVIDIA GeForce RTX 5090 Mobile

Head-to-Head Benchmarks

The data shows a decisive performance advantage for the NVIDIA GeForce RTX 5090 Mobile, although the comparison is limited because the AMD Radeon AI PRO 9600D has no recorded benchmark scores in the database. The RTX 5090 Mobile delivers an average benchmark score of 45,152, placing it in the 84th percentile of all GPUs. The AMD part, with an average score of 0 and a 50th percentile ranking, has no measurable results to compare directly. Consequently, the wins column records zero victories for the AMD card and zero for the NVIDIA card, but the available evidence strongly favors the NVIDIA solution.

The RTX 5090 Mobile’s benchmark suite reveals its strengths. In 3DMark Steel Nomad (DX12), it scores 5,871. Its Geekbench results are particularly strong: 201,834 in OpenCL and 198,405 in Vulkan. PassMark results show a G3D score of 30,034, a GPU compute score of 13,401, and a G2D score of 1,057. Older DirectX tests also register: DX9 at 324, DX11 at 269, DX10 at 183, and DX12 at 138. These figures indicate a GPU that performs consistently across compute and graphics workloads, with the OpenCL score being the standout.

Relative to its nearest rivals, the RTX 5090 Mobile sits in a tight competitive band. It is 0.5% behind the AMD Radeon Pro 5500 XT (which scores 45,384), 0.8% ahead of the NVIDIA GeForce RTX 4070 Ti (44,795), 1% behind the Intel Arc A730M (45,592), and 1.8% behind the NVIDIA RTX 5880 Ada Generation (45,972). The delta percentages are small, suggesting that the RTX 5090 Mobile is not a dominant outlier but rather a strong performer within a cluster of high-end parts. Its 84th percentile placement confirms this, as it outperforms the vast majority of GPUs in the database while trailing a few specialized workstation and desktop cards.

For the AMD Radeon AI PRO 9600D, the absence of benchmark data means no quantitative conclusions can be drawn about its real-world speed. The database lists no tests, no scores, and no rival comparisons. This is a significant gap for a product with an Active production status. Users seeking to compare these two directly must rely on the NVIDIA card’s recorded results and the AMD card’s architectural specifications, which are detailed later in this analysis.

FAQ

Q: Which GPU has a higher average benchmark score?

A: The NVIDIA GeForce RTX 5090 Mobile has an average benchmark score of 45,152, while the AMD Radeon AI PRO 9600D has an average score of 0 because no benchmark results are recorded for it.

Q: How does the RTX 5090 Mobile compare to its nearest rivals?

A: The RTX 5090 Mobile is 0.5% behind the AMD Radeon Pro 5500 XT, 0.8% ahead of the NVIDIA GeForce RTX 4070 Ti, 1% behind the Intel Arc A730M, and 1.8% behind the NVIDIA RTX 5880 Ada Generation.

Q: What is the memory configuration of each GPU?

A: The AMD Radeon AI PRO 9600D uses 32 GB of GDDR6 memory on a 256-bit bus with 576.0 GB/s bandwidth. The NVIDIA GeForce RTX 5090 Mobile uses 24 GB of GDDR7 memory on a 256-bit bus with 896.0 GB/s bandwidth.

Q: Which GPU has higher FP32 compute throughput?

A: The NVIDIA GeForce RTX 5090 Mobile delivers 31.80 TFLOPS of FP32 performance, compared to 24.82 TFLOPS for the AMD Radeon AI PRO 9600D.

Q: What is the power consumption difference?

A: The AMD Radeon AI PRO 9600D has a TDP of 150 W, while the NVIDIA GeForce RTX 5090 Mobile has a TDP of 95 W.

Q: Which GPU has more shading units?

A: The NVIDIA GeForce RTX 5090 Mobile has 10,496 shading units, while the AMD Radeon AI PRO 9600D has 3,072.

The Verdict

The data points to the NVIDIA GeForce RTX 5090 Mobile as the superior choice for performance-focused users. Its recorded benchmark scores, 84th percentile ranking, and higher FP32 throughput make it the clear winner in raw compute. The RTX 5090 Mobile also leads in texture rate (496.9 GTexel/s vs 387.8 GTexel/s) and pixel rate (169.7 GPixel/s vs 193.9 GPixel/s, though the AMD part is higher here). However, the AMD Radeon AI PRO 9600D is not without merit, particularly for workloads that demand large memory capacity.

The RTX 5090 Mobile is the pick for users who prioritize speed, as evidenced by its 30% advantage in FP32 (31.80 TFLOPS vs 24.82 TFLOPS) and its 55% higher memory bandwidth (896.0 GB/s vs 576.0 GB/s). The AMD card, with 32 GB of memory, is better suited for scenarios where capacity outweighs throughput, such as large dataset processing or high-resolution texture storage. The RTX 5090 Mobile’s 24 GB is still substantial, but the AMD part offers a third more memory.

Given the absence of AMD benchmark data, the RTX 5090 Mobile’s verified results are the only quantifiable basis for a decision. Users who need proven performance should select the NVIDIA card. Users who need maximum memory capacity and can tolerate unverified performance should consider the AMD card.

Specification Differences

The two GPUs differ across nearly every specification. The AMD Radeon AI PRO 9600D uses a 4 nm process node, while the NVIDIA GeForce RTX 5090 Mobile uses a 5 nm node. The AMD chip, Navi 48, contains 53,900 million transistors on a 357 mm² die, resulting in a transistor density of 151.0M per mm². The NVIDIA chip, GB203, contains 45,600 million transistors on a 378 mm² die, with a density of 120.6M per mm².

Clock speeds vary significantly. The AMD part has a base clock of 1080 MHz and a boost clock of 2020 MHz. The NVIDIA part has a base clock of 990 MHz and a boost clock of 1515 MHz. The AMD card’s higher boost clock suggests better per-clock efficiency, but the NVIDIA card compensates with far more execution units.

Memory specifications diverge sharply. The AMD card offers 32 GB of GDDR6, while the NVIDIA card offers 24 GB of GDDR7. Both use a 256-bit bus, but the NVIDIA card’s GDDR7 memory runs at 1750 MHz (28 Gbps effective) versus 2250 MHz (18 Gbps effective) for the AMD card. This yields bandwidth of 896.0 GB/s for NVIDIA and 576.0 GB/s for AMD.

The compute unit counts favor NVIDIA overwhelmingly. The RTX 5090 Mobile has 10,496 shading units, 328 texture mapping units, 112 ROPs, 82 RT cores, and 328 tensor cores. The AMD card has 3,072 shading units, 192 TMUs, 96 ROPs, and 48 RT cores, with no tensor cores listed. The NVIDIA card’s FP32 output is 31.80 TFLOPS versus 24.82 TFLOPS for AMD.

Power and physical characteristics differ as well. The AMD card has a TDP of 150 W, is single-slot, uses a 1x 16-pin power connector, and requires a 450 W suggested PSU. The NVIDIA card has a TDP of 95 W, is an integrated GPU (IGP) with no power connectors, and lists no suggested PSU. The AMD card measures 241 mm in length, 111 mm in height, and 19 mm in width, while the NVIDIA card has no recorded dimensions.

Architecture Differences

The architectural divide is fundamental. The AMD Radeon AI PRO 9600D is built on RDNA 4.0 architecture, part of the Radeon Pro Navi generation (Navi IV Series). The NVIDIA GeForce RTX 5090 Mobile uses Blackwell 2.0 architecture, part of the GeForce 50 Mobile generation. Both are fabricated by TSMC, but on different nodes: AMD uses 4 nm, NVIDIA uses 5 nm.

The AMD chip, Navi 48, has a higher transistor density (151.0M per mm²) despite a smaller die (357 mm² vs 378 mm²) and fewer total transistors (53,900 million vs 45,600 million). This suggests a more compact design, but the NVIDIA chip packs more execution resources into a slightly larger area.

The NVIDIA card includes 328 tensor cores, which are absent from the AMD specification. This is a critical difference for AI and machine learning workloads, as tensor cores accelerate matrix operations. The AMD card has no equivalent listed. RT core counts also favor NVIDIA: 82 versus 48 for AMD.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4, so API compatibility is identical. The AMD card outputs via 1x DisplayPort 2.1a, while the NVIDIA card’s display outputs are described as "Portable Device Dependent," reflecting its mobile design. The AMD card is a discrete, single-slot solution; the NVIDIA card is an integrated GPU (IGP).

Where Each One Wins

The NVIDIA GeForce RTX 5090 Mobile wins decisively in compute throughput. Its FP32 output of 31.80 TFLOPS exceeds the AMD card’s 24.82 TFLOPS by roughly 28%. Texture rate also favors NVIDIA: 496.9 GTexel/s versus 387.8 GTexel/s, a 28% advantage. Memory bandwidth is even more lopsided: 896.0 GB/s versus 576.0 GB/s, a 55% margin. These figures indicate that the RTX 5090 Mobile is better for gaming, rendering, and any workload that stresses raw fill rates or memory access.

The AMD Radeon AI PRO 9600D wins in memory capacity, offering 32 GB versus 24 GB. This is a 33% advantage, which matters for applications that load very large textures, datasets, or models into VRAM. The AMD card also has a higher pixel rate (193.9 GPixel/s vs 169.7 GPixel/s), suggesting a slight edge in pure rasterization throughput per clock, though this is offset by NVIDIA’s higher texture rate.

The RTX 5090 Mobile’s tensor cores give it a clear advantage in AI inference and training workloads, while the AMD card has no tensor core specification. The NVIDIA card’s lower TDP (95 W vs 150 W) also makes it more suitable for power-constrained mobile systems, despite its higher compute output.

The AMD card wins on process node efficiency, using a smaller 4 nm node versus 5 nm, and on transistor density (151.0M per mm² vs 120.6M per mm²). These architectural advantages do not translate into benchmark wins, however, because no AMD benchmark data exists. The recorded data confirms that the RTX 5090 Mobile is the stronger performer, while the AMD card remains a viable option only for users who specifically need 32 GB of memory and can forgo verified performance metrics.

DETAILED SPECIFICATIONS

SPECIFICATION
AI PRO 9600D
RTX 5090 Mobile
Core Specs
Shading Units
3,072
10,496 +241.7%
Shaders
3,072
10,496 +241.7%
TMUs
192
328 +70.8%
ROPs
96
112 +16.7%
Compute Units
48
—
SM Count
—
82
Clocks
Base Clock
1080 MHz
990 MHz
Boost Clock
2020 MHz
1515 MHz
Game Clock
1080 MHz
—
Memory Clock
2250 MHz 18 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
32 GB
24 GB
VRAM (MB)
32,768
24,576 -25.0%
Memory Type
GDDR6
GDDR7
Memory Bus
256 bit
256 bit
Bandwidth
576.0 GB/s
896.0 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
8 MB
64 MB
L3 Cache
48 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
193.9 GPixel/s
169.7 GPixel/s
Texture Rate
387.8 GTexel/s
496.9 GTexel/s
FP32 (TFLOPS)
24.82 TFLOPS
31.80 TFLOPS
FP64 (TFLOPS)
775.7 GFLOPS (1:32)
496.9 GFLOPS (1:64)
FP16 (TFLOPS)
24.82 TFLOPS (1:1)
31.80 TFLOPS (1:1)
AI/RT
RT Cores
48
82 +70.8%
Tensor Cores
—
328
Matrix Cores
96
—
Power
TDP
150 W
95 W
TDP (W)
150
95 -36.7%
Suggested PSU
450 W
—
Power Connectors
1x 16-pin
None
Architecture
Architecture
RDNA 4.0
Blackwell 2.0
GPU Name
Navi 48
GB203
Generation
Radeon Pro Navi (Navi IV Series)
GeForce 50 Mobile
Process Size
4 nm
5 nm
Transistors
53,900 million
45,600 million
Die Size
357 mm²
378 mm²
Foundry
TSMC
TSMC
Density
151.0M / mm²
120.6M / mm²
API Support
DirectX
12 Ultimate (12_2)
12 Ultimate (12_2)
OpenGL
4.6
4.6
Vulkan
1.4
1.4
OpenCL
2.2
3.0
CUDA
—
12.0
Shader Model
6.9
6.9
Physical
Slot Width
Single-slot
IGP
Length
241 mm 9.5 inches
—
Height
111 mm 4.4 inches
—
Outputs
1x DisplayPort 2.1a
Portable Device Dependent
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Other
Production
Active
Active
Predecessor
Radeon Pro Vega
GeForce 40 Mobile
View Radeon AI PRO 9600D Details View GeForce RTX 5090 Mobile Details