AMD Radeon RX 9060 XT LP vs NVIDIA GeForce RTX 4070 SUPER Comparison

AMD
RADEON

AMD Radeon RX 9060 XT LP

CORE STATE Navi 44
VRAM 16 GB
CLOCK SPEED 3050 MHz
TDP 140 W
BUS WIDTH 128 bit
ARCHITECTURE RDNA 4.0
nm
PROCESS 4 nm
LAUNCH DATE 2025
VS
NVIDIA
GEFORCE

GeForce RTX 4070 SUPER

CORE STATE AD104
VRAM 12 GB
CLOCK SPEED 2475 MHz
TDP 220 W
BUS WIDTH 192 bit
ARCHITECTURE Ada Lovelace
nm
PROCESS 5 nm
LAUNCH DATE 2024

PERFORMANCE BENCHMARKS

geekbench_opencl
88,183
172,795
geekbench_vulkan
39,476
205,624
3dmark_3dmark_steel_nomad_dx12
N/A
4,627
passmark_directx_10
N/A
167
passmark_directx_11
N/A
273
passmark_directx_12
N/A
110
passmark_directx_9
N/A
344
passmark_g2d
N/A
1,184
passmark_g3d
N/A
29,995
passmark_gpu_compute
N/A
17,108

Analysis: AMD Radeon RX 9060 XT LP vs NVIDIA GeForce RTX 4070 SUPER

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 9060 XT LP has a significantly higher average benchmark score of 63,830, compared to the NVIDIA GeForce RTX 4070 SUPER's 43,223. The AMD card sits in the 89th percentile of all GPUs, while the NVIDIA card is in the 83rd percentile.

Q: How do the two cards compare in the Geekbench OpenCL test?

A: The NVIDIA GeForce RTX 4070 SUPER scores 172,795 in Geekbench OpenCL, which is 49% higher than the AMD Radeon RX 9060 XT LP's score of 88,183. This is a substantial margin in favor of NVIDIA.

Q: What is the difference in the Geekbench Vulkan benchmark?

A: The NVIDIA card dominates the Vulkan test with a score of 205,624, while the AMD card scores 39,476. This represents an 80.8% advantage for the NVIDIA GeForce RTX 4070 SUPER.

Q: Which card has more memory?

A: The AMD Radeon RX 9060 XT LP has 16 GB of GDDR6 memory, while the NVIDIA GeForce RTX 4070 SUPER has 12 GB of GDDR6X memory. AMD's card offers more capacity, but NVIDIA's card has a wider 192-bit bus and higher bandwidth.

Q: What are the power requirements for each card?

A: The AMD Radeon RX 9060 XT LP has a TDP of 140 W and requires a 300 W power supply. The NVIDIA GeForce RTX 4070 SUPER has a TDP of 220 W and requires a 550 W power supply.

Q: What is the production status of each GPU?

A: The AMD Radeon RX 9060 XT LP is listed as Active production, released on 2025-12-16. The NVIDIA GeForce RTX 4070 SUPER is listed as End-of-life, released on 2024-01-16, with a successor in the GeForce 50 series.

Architecture Differences

The AMD Radeon RX 9060 XT LP uses the Navi 44 chip built on RDNA 4.0 architecture, fabricated on a 4 nm TSMC process. The NVIDIA GeForce RTX 4070 SUPER uses the AD104 chip with Ada Lovelace architecture on a 5 nm TSMC process. This node difference gives AMD a higher transistor density of 149.2 million transistors per square millimeter versus 121.8 million for NVIDIA. AMD's die is 199 mm² with 29,700 million transistors, while NVIDIA's die is larger at 294 mm² with 35,800 million transistors.

The AMD card features 2,048 shading units, 128 texture mapping units, and 64 render output units. It also has 32 ray tracing cores but no tensor cores. The NVIDIA card is configured differently with 7,168 shading units, 224 TMUs, and 80 ROPs. It has 56 ray tracing cores and 224 tensor cores, the latter enabling dedicated AI acceleration that the AMD card lacks entirely.

Both cards support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The memory architectures differ substantially: AMD pairs 16 GB of GDDR6 on a 128-bit bus with 322.3 GB/s of bandwidth, while NVIDIA pairs 12 GB of GDDR6X on a 192-bit bus with 504.2 GB/s of bandwidth. The bus interface also differs, with AMD using PCIe 5.0 x16 and NVIDIA using PCIe 4.0 x16.

Clock behavior diverges as well. The AMD card lists a base clock of 1380 MHz, a boost clock of 3050 MHz, and a game clock of 2450 MHz. The NVIDIA card has a higher base clock of 1980 MHz but a lower boost clock of 2475 MHz. Memory clocks are 2518 MHz (20.1 Gbps effective) for AMD and 1313 MHz (21 Gbps effective) for NVIDIA.

Head-to-Head Benchmarks

The recorded head-to-head data contains two benchmark comparisons, and NVIDIA wins both. In Geekbench OpenCL, the NVIDIA GeForce RTX 4070 SUPER scores 172,795 against the AMD Radeon RX 9060 XT LP's 88,183, a delta of 49% in NVIDIA's favor. This result indicates that in OpenCL compute workloads, NVIDIA holds a commanding lead.

The Geekbench Vulkan test shows an even wider gap. NVIDIA scores 205,624 while AMD scores 39,476, a delta of 80.8%. This is a dominant result for the NVIDIA card, suggesting that Vulkan API performance strongly favors Ada Lovelace in this measurement.

The AMD card's average benchmark score of 63,830 across all recorded benchmarks is higher than NVIDIA's 43,223, yet the head-to-head tests tell a different story. The disparity arises because the average includes different benchmark suites and the NVIDIA card has a broader set of recorded results, including multiple Passmark tests. In the two directly comparable tests, NVIDIA is clearly ahead.

Looking at the nearest rivals in the database, the AMD Radeon RX 9060 XT LP sits close to cards like the NVIDIA CMP 30HX (delta 0%) and the AMD Radeon RX 7600M (delta 0.1%). The NVIDIA GeForce RTX 4070 SUPER sits near the NVIDIA Quadro M6000 24 GB (delta -0.1%) and the NVIDIA GeForce RTX 5050 Mobile (delta -0.1%). These reference points place both cards in different performance tiers despite the AMD card's higher average score.

Specification Differences

| Specification | AMD Radeon RX 9060 XT LP | NVIDIA GeForce RTX 4070 SUPER |

|---|---|---|

| Architecture | RDNA 4.0 | Ada Lovelace |

| Process node | 4 nm | 5 nm |

| Transistors | 29,700 million | 35,800 million |

| Die size | 199 mm² | 294 mm² |

| Transistor density | 149.2M / mm² | 121.8M / mm² |

| Base clock | 1380 MHz | 1980 MHz |

| Boost clock | 3050 MHz | 2475 MHz |

| Memory size | 16 GB | 12 GB |

| Memory type | GDDR6 | GDDR6X |

| Memory bus | 128 bit | 192 bit |

| Memory bandwidth | 322.3 GB/s | 504.2 GB/s |

| Shading units | 2048 | 7168 |

| TMUs | 128 | 224 |

| ROPs | 64 | 80 |

| RT cores | 32 | 56 |

| Tensor cores | None | 224 |

| FP32 | 24.99 TFLOPS | 35.48 TFLOPS |

| FP16 | 24.99 TFLOPS (1:1) | 35.48 TFLOPS (1:1) |

| Pixel rate | 195.2 GPixel/s | 198.0 GPixel/s |

| Texture rate | 390.4 GTexel/s | 554.4 GTexel/s |

| TDP | 140 W | 220 W |

| Power connector | 1x 8-pin | 1x 16-pin |

| Suggested PSU | 300 W | 550 W |

| Bus interface | PCIe 5.0 x16 | PCIe 4.0 x16 |

| Display outputs | 1x HDMI 2.1b, 2x DisplayPort 2.1a | 1x HDMI 2.1, 3x DisplayPort 1.4a |

| Release date | 2025-12-16 | 2024-01-16 |

| Production status | Active | End-of-life |

| Launch MSRP | None recorded | 599 USD |

Where Each One Wins

The NVIDIA GeForce RTX 4070 SUPER wins decisively in the recorded head-to-head compute benchmarks. Its Geekbench OpenCL score of 172,795 is nearly double the AMD card's 88,183, and its Geekbench Vulkan score of 205,624 is more than five times the AMD card's 39,476. These results place NVIDIA ahead for compute-oriented workloads measured through those APIs. The NVIDIA card also has higher raw throughput specifications, including 35.48 TFLOPS FP32 versus 24.99 TFLOPS for AMD, a higher texture rate of 554.4 GTexel/s versus 390.4 GTexel/s, and a higher memory bandwidth of 504.2 GB/s versus 322.3 GB/s. The 224 tensor cores provide dedicated AI acceleration capability that the AMD card cannot match.

The AMD Radeon RX 9060 XT LP wins in efficiency and capacity metrics. Its TDP of 140 W is 80 W lower than NVIDIA's 220 W, and its suggested PSU of 300 W is substantially lower than NVIDIA's 550 W requirement. The 16 GB memory capacity exceeds NVIDIA's 12 GB, which matters for workloads that require larger frame buffers. The AMD card uses a PCIe 5.0 x16 interface versus PCIe 4.0 x16 for NVIDIA, offering double the interface bandwidth. Its 4 nm process node with higher transistor density of 149.2M per mm² indicates a more compact design. The average benchmark score of 63,830 versus 43,223 also favors AMD, as does the 89th percentile ranking versus NVIDIA's 83rd. The AMD card is in active production, while the NVIDIA card is end-of-life.

The Verdict

The recorded data shows two GPUs with different strengths. The NVIDIA GeForce RTX 4070 SUPER is the clear winner in the two directly comparable benchmark tests, delivering 49% higher Geekbench OpenCL performance and 80.8% higher Geekbench Vulkan performance. Its compute specifications are uniformly higher: more shading units, more ray tracing cores, more texture units, higher FP32 throughput, and higher memory bandwidth. For users prioritizing measured compute performance in OpenCL and Vulkan, the NVIDIA card is the data-backed choice.

The AMD Radeon RX 9060 XT LP counters with a higher average benchmark score of 63,830, a higher percentile ranking of 89 versus 83, double the tensor-free compute of its own configuration, and a lower power envelope. Its 140 W TDP and 300 W suggested PSU make it suitable for systems with smaller power budgets. The 16 GB memory capacity is larger, and the active production status ensures ongoing availability. The NVIDIA card's end-of-life status and its 599 USD launch MSRP provide additional context for its position in the market.

Users who need maximum compute performance in OpenCL and Vulkan workloads should select the NVIDIA GeForce RTX 4070 SUPER based on its decisive benchmark margins. Users who require lower power draw, larger memory capacity, PCIe 5.0 connectivity, and active production support should select the AMD Radeon RX 9060 XT LP. The two cards address different priorities, and the benchmark data clearly separates them along those lines.

DETAILED SPECIFICATIONS

SPECIFICATION
RX 9060 XT LP
RTX 4070 SUPER
Core Specs
Shading Units
2,048
7,168 +250.0%
Shaders
2,048
7,168 +250.0%
TMUs
128
224 +75.0%
ROPs
64
80 +25.0%
Compute Units
32
—
SM Count
—
56
Clocks
Base Clock
1380 MHz
1980 MHz
Boost Clock
3050 MHz
2475 MHz
Game Clock
2450 MHz
—
Memory Clock
2518 MHz 20.1 Gbps effective
1313 MHz 21 Gbps effective
Memory
Memory Size
16 GB
12 GB
VRAM (MB)
16,384
12,288 -25.0%
Memory Type
GDDR6
GDDR6X
Memory Bus
128 bit
192 bit
Bandwidth
322.3 GB/s
504.2 GB/s
Cache
L1 Cache
—
128 KB (per SM)
L2 Cache
4 MB
48 MB
L3 Cache
32 MB
—
L0 Cache
32 KB per WGP
—
Performance
Pixel Rate
195.2 GPixel/s
198.0 GPixel/s
Texture Rate
390.4 GTexel/s
554.4 GTexel/s
FP32 (TFLOPS)
24.99 TFLOPS
35.48 TFLOPS
FP64 (TFLOPS)
780.8 GFLOPS (1:32)
554.4 GFLOPS (1:64)
FP16 (TFLOPS)
24.99 TFLOPS (1:1)
35.48 TFLOPS (1:1)
AI/RT
RT Cores
32
56 +75.0%
Tensor Cores
—
224
Matrix Cores
64
—
Power
TDP
140 W
220 W
TDP (W)
140
220 +57.1%
Suggested PSU
300 W
550 W
Power Connectors
1x 8-pin
1x 16-pin
Architecture
Architecture
RDNA 4.0
Ada Lovelace
GPU Name
Navi 44
AD104
Generation
Navi IV (RX 9000)
GeForce 40
Process Size
4 nm
5 nm
Transistors
29,700 million
35,800 million
Die Size
199 mm²
294 mm²
Foundry
TSMC
TSMC
Density
149.2M / mm²
121.8M / 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
—
8.9
Shader Model
6.9
6.9
Physical
Slot Width
Dual-slot
Dual-slot
Length
—
267 mm 10.5 inches
Height
—
112 mm 4.4 inches
Outputs
1x HDMI 2.1b2x DisplayPort 2.1a
1x HDMI 2.13x DisplayPort 1.4a
Bus Interface
PCIe 5.0 x16
PCIe 4.0 x16
Other
Launch Price
—
599 USD
Production
Active
End-of-life
Predecessor
Navi III
GeForce 30
Successor
—
GeForce 50
View Radeon RX 9060 XT LP Details View GeForce RTX 4070 SUPER Details