AMD Radeon RX 9060 XT 16 GB vs NVIDIA GeForce RTX 5090 SE Comparison

AMD
RADEON

AMD Radeon RX 9060 XT 16 GB

CORE STATE Navi 44
VRAM 16 GB
CLOCK SPEED 3130 MHz
TDP 160 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 4.0
nm
PROCESS 4 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

GeForce RTX 5090 SE

CORE STATE GB202
VRAM 24 GB
CLOCK SPEED 2377 MHz
TDP 500 W
BUS WIDTH 384 bit
ARCHITECTURE Blackwell 2.0
nm
PROCESS 5 nm
LAUNCH DATE 2026

PERFORMANCE BENCHMARKS

3dmark_3dmark_steel_nomad_dx12
4,093
N/A
passmark_directx_10
116
N/A
passmark_directx_11
185
N/A
passmark_directx_12
57
N/A
passmark_directx_9
305
N/A
passmark_g2d
1,169
N/A
passmark_g3d
20,099
N/A
passmark_gpu_compute
11,234
N/A

Analysis: AMD Radeon RX 9060 XT 16 GB vs NVIDIA GeForce RTX 5090 SE

Where Each One Wins

The AMD Radeon RX 9060 XT 16 GB and the NVIDIA GeForce RTX 5090 SE occupy distinctly different positions in the benchmark database. The AMD card belongs to the Radeon RX 9000 series, built on the Navi 44 chip with RDNA 4.0 architecture, and it has a complete set of recorded measurements. The NVIDIA card, part of the GeForce 50-series with the GB202 chip and Blackwell 2.0 architecture, currently has no benchmark entries in the database, which limits direct comparison to architectural and specification analysis rather than measured performance.

The RX 9060 XT shows a percentile rank of 27 among all GPUs in the database, meaning it outperforms roughly a quarter of all recorded graphics cards. Its average benchmark score stands at 4657 across eight tests. The RTX 5090 SE carries a percentile rank of 50, indicating it sits at the median of all recorded GPUs, though this ranking is based on its specification profile rather than actual benchmark results, as its measured average score is zero.

The AMD card wins on the basis of having measurable performance data at all. Its benchmark suite includes 3DMark Steel Nomad DX12 with a score of 4093, PassMark G3D at 20099, PassMark GPU Compute at 11234, and several legacy DirectX tests. The NVIDIA card has no such measurements, so any claim of superiority for either product must rest on architectural specifications rather than head-to-head results.

Architecture Differences

The two GPUs differ fundamentally in their silicon design. AMD uses a 4 nm TSMC process for the Navi 44 chip, which contains 29,700 million transistors on a 199 mm² die, yielding a transistor density of 149.2 million per square millimeter. NVIDIA's GB202 chip uses a 5 nm TSMC process, packs 92,200 million transistors onto a 750 mm² die, and achieves a lower density of 122.9 million per square millimeter. The larger die and higher transistor count give NVIDIA a substantial physical advantage in raw compute resources.

Clock behavior diverges sharply. The AMD card has a base clock of 1700 MHz, a boost clock of 3130 MHz, and a game clock of 2530 MHz. The NVIDIA card runs a base clock of 1740 MHz and a boost clock of 2377 MHz, with no game clock specified. Despite the lower boost ceiling, NVIDIA's architecture compensates with far more execution units: 14,080 shading units versus 2,048, 440 texture mapping units versus 128, and 160 ROPs versus 64.

Ray tracing and tensor hardware show the most pronounced gap. AMD provides 32 ray accelerators and no tensor cores. NVIDIA supplies 110 RT cores and 440 tensor cores, the latter being critical for AI workloads and DLSS-style features. The API support is identical: both cards expose DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Memory subsystems differ in capacity, type, and bandwidth. The RX 9060 XT uses 16 GB of GDDR6 on a 128-bit bus, delivering 322.3 GB/s. The RTX 5090 SE uses 24 GB of GDDR7 on a 384-bit bus, delivering 1.34 TB/s, which is more than four times the AMD card's bandwidth. Effective memory speed is 20.1 Gbps for AMD versus 28 Gbps for NVIDIA.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two cards, and the wins counter shows zero for each side. The AMD card has eight individual benchmark scores; the NVIDIA card has none. This absence of measured data means the nearest-rival analysis applies only to the RX 9060 XT.

The RX 9060 XT's nearest rivals in the database are all significantly older or lower-tier products. Its average score of 4657 exactly matches the AMD Radeon R5 M320, a mobile entry-level part. The NVIDIA Quadro P400 scores 4684, which is 0.6% higher than the RX 9060 XT. The NVIDIA GeForce GTX 970M scores 4628, 0.6% lower, and the NVIDIA Quadro M3000M scores 4621, 0.8% lower. These deltas are all within one percent, indicating that the RX 9060 XT's measured performance lands in a very narrow band around these older products.

For the RTX 5090 SE, no nearest rivals exist in the database. Its percentile rank of 50 suggests it is positioned at the median of all GPUs, but without benchmark scores, this rank cannot be verified against actual measurements. The specification sheet indicates a far higher compute ceiling: FP32 performance of 66.94 TFLOPS versus 25.64 TFLOPS for the AMD card, and pixel rate of 380.3 GPixel/s versus 200.3 GPixel/s. Texture rate also favors NVIDIA heavily at 1,045.9 GTexel/s compared to 400.6 GTexel/s.

FAQ

Q: Which card has higher FP32 compute performance?

A: The NVIDIA GeForce RTX 5090 SE delivers 66.94 TFLOPS of FP32 performance, while the AMD Radeon RX 9060 XT 16 GB delivers 25.64 TFLOPS. The NVIDIA card also matches its FP16 output at 66.94 TFLOPS, whereas AMD's FP16 is also 25.64 TFLOPS with a 1:1 ratio.

Q: How do the memory configurations compare?

A: The AMD card uses 16 GB of GDDR6 on a 128-bit bus with 322.3 GB/s bandwidth. The NVIDIA card uses 24 GB of GDDR7 on a 384-bit bus with 1.34 TB/s bandwidth. NVIDIA's effective memory speed is 28 Gbps versus AMD's 20.1 Gbps.

Q: What is the transistor count difference?

A: The RX 9060 XT's Navi 44 chip contains 29,700 million transistors on a 199 mm² die. The RTX 5090 SE's GB202 chip contains 92,200 million transistors on a 750 mm² die. The transistor density is 149.2 million per mm² for AMD and 122.9 million per mm² for NVIDIA.

Q: Do both cards support the same APIs?

A: Yes, both cards expose DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The RTX 5090 SE adds 440 tensor cores for AI acceleration, which the RX 9060 XT does not have.

Q: What are the power requirements?

A: The RX 9060 XT has a TDP of 160 W and uses a single 8-pin power connector, with a suggested PSU rating of 450 W. The RTX 5090 SE has a TDP of 500 W and uses a single 16-pin connector, with a suggested PSU rating of 900 W.

Q: How does the RX 9060 XT compare to its nearest database rivals?

A: Its average benchmark score of 4657 is identical to the AMD Radeon R5 M320. It trails the NVIDIA Quadro P400 by 0.6%, beats the GeForce GTX 970M by 0.6%, and beats the Quadro M3000M by 0.8%.

Specification Differences

The following fields differ between the two cards. Identical fields, such as PCIe 5.0 x16 bus interface, dual-slot width, and API support, are omitted.

Process and die: AMD uses 4 nm TSMC with 29,700 million transistors on 199 mm². NVIDIA uses 5 nm TSMC with 92,200 million transistors on 750 mm². Transistor density is 149.2M/mm² for AMD and 122.9M/mm² for NVIDIA.

Clocks: AMD has base 1700 MHz, boost 3130 MHz, game 2530 MHz. NVIDIA has base 1740 MHz, boost 2377 MHz, and no game clock.

Memory: AMD has 16 GB GDDR6 on 128-bit with 322.3 GB/s and 20.1 Gbps effective. NVIDIA has 24 GB GDDR7 on 384-bit with 1.34 TB/s and 28 Gbps effective.

Compute units: AMD has 2,048 shading units, 128 TMUs, 64 ROPs, 32 RT cores, no tensor cores. NVIDIA has 14,080 shading units, 440 TMUs, 160 ROPs, 110 RT cores, 440 tensor cores.

Rates: AMD has 200.3 GPixel/s, 400.6 GTexel/s, 25.64 TFLOPS FP32 and FP16. NVIDIA has 380.3 GPixel/s, 1,045.9 GTexel/s, 66.94 TFLOPS FP32 and FP16.

Power: AMD has 160 W TDP, 1x 8-pin connector, 450 W suggested PSU. NVIDIA has 500 W TDP, 1x 16-pin connector, 900 W suggested PSU.

Display outputs: AMD has 1x HDMI 2.1b and 2x DisplayPort 2.1a. NVIDIA has 1x HDMI 2.1b and 3x DisplayPort 2.1b.

Physical dimensions: AMD lists no length, height, or width. NVIDIA measures 267 mm length, 111 mm height, and 40 mm width.

Release and lifecycle: AMD released 2025-06-03, predecessor Navi III, no successor. NVIDIA released 2025-12-31, predecessor GeForce 40, successor GeForce 60.

Launch MSRP: AMD is 349 USD. NVIDIA is 1,499 USD.

Benchmark presence: AMD has eight recorded benchmark scores with a 27th percentile rank and 4657 average. NVIDIA has zero recorded benchmark scores with a 50th percentile rank and zero average.

The data shows a clear division: the RX 9060 XT is a measured, entry-to-mid-range product with verified scores against older rivals, while the RTX 5090 SE is a high-specification product whose benchmark results have not yet been recorded. The architectural gap, especially in shading units, memory bandwidth, and tensor core count, suggests the NVIDIA card would dominate in compute-heavy workloads, but the database currently lacks the evidence to quantify that advantage.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 9060 XT 16 GB
RTX 5090 SE
Core Specs
Shading Units
2,048
14,080 +587.5%
Shaders
2,048
14,080 +587.5%
TMUs
128
440 +243.8%
ROPs
64
160 +150.0%
Compute Units
32
—
SM Count
—
110
Clocks
Base Clock
1700 MHz
1740 MHz
Boost Clock
3130 MHz
2377 MHz
Game Clock
2530 MHz
—
Memory Clock
2518 MHz 20.1 Gbps effective
1750 MHz 28 Gbps effective
Memory
Memory Size
16 GB
24 GB
VRAM (MB)
16,384
24,576 +50.0%
Memory Type
GDDR6
GDDR7
Memory Bus
128 bit
384 bit
Bandwidth
322.3 GB/s
1.34 TB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
4 MB
96 MB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
200.3 GPixel/s
380.3 GPixel/s
Texture Rate
400.6 GTexel/s
1,045.9 GTexel/s
FP32 (TFLOPS)
25.64 TFLOPS
66.94 TFLOPS
FP64 (TFLOPS)
801.3 GFLOPS (1:32)
1,045.9 GFLOPS (1:64)
FP16 (TFLOPS)
25.64 TFLOPS (1:1)
66.94 TFLOPS (1:1)
AI/RT
RT Cores
32
110 +243.8%
Tensor Cores
—
440
Matrix Cores
64
—
Power
TDP
160 W
500 W
TDP (W)
160
500 +212.5%
Suggested PSU
450 W
900 W
Power Connectors
1x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 4.0
Blackwell 2.0
GPU Name
Navi 44
GB202
Codename
Strix Point
—
Generation
Navi IV (RX 9000)
GeForce 50
Process Size
4 nm
5 nm
Transistors
29,700 million
92,200 million
Die Size
199 mm²
750 mm²
Foundry
TSMC
TSMC
Density
149.2M / mm²
122.9M / 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
Dual-slot
Dual-slot
Length
—
267 mm 10.5 inches
Height
—
111 mm 4.4 inches
Outputs
1x HDMI 2.1b2x DisplayPort 2.1a
1x HDMI 2.1b3x DisplayPort 2.1b
Bus Interface
PCIe 5.0 x16
PCIe 5.0 x16
Other
Launch Price
349 USD
1,499 USD
Production
Active
Active
Predecessor
Navi III
GeForce 40
Successor
—
GeForce 60
View Radeon RX 9060 XT 16 GB Details View GeForce RTX 5090 SE Details