AMD Radeon RX 9060 XT LP vs AMD Radeon RX 9070 GRE Comparison
AMD Radeon RX 9060 XT LP
Radeon RX 9070 GRE
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon RX 9060 XT LP vs AMD Radeon RX 9070 GRE
Head-to-Head Benchmarks
The benchmark comparison between the AMD Radeon RX 9060 XT LP and the AMD Radeon RX 9070 GRE produces a decisive outcome in the single directly comparable test. The Geekbench OpenCL result shows the RX 9070 GRE scoring 109,309 points against the RX 9060 XT LP’s 88,183 points. That represents a 19.3% advantage for the larger card, a substantial margin that establishes a clear performance hierarchy between these two RDNA 4.0 parts.
The RX 9060 XT LP does hold a different kind of advantage, however. Its average benchmark score across all tested workloads stands at 63,830, placing it in the 89th percentile of all GPUs. The RX 9070 GRE, by contrast, averages 57,367 and sits in the 87th percentile. This is an unusual inversion. The RX 9070 GRE wins the head-to-head OpenCL test by a wide margin, yet its overall average is lower because it has only two recorded benchmarks, one of which is a demanding 3DMark Steel Nomad DX12 run that scores 5,424. The RX 9060 XT LP’s average draws from two Geekbench tests, both of which are more favorable to its architectural profile.
When placed against their nearest rivals, the two cards occupy different competitive tiers. The RX 9060 XT LP trades blows with the NVIDIA CMP 30HX (delta 0%), the AMD Radeon RX 7600M (delta 0.1%), and the AMD Radeon Pro Vega 56 (delta 0.2%), while trailing the AMD Radeon Pro WX 9100 by 0.6%. The RX 9070 GRE, meanwhile, sits marginally behind the Intel Arc A580 by 0.7%, the AMD Radeon RX 5600 OEM by 1.2%, the Intel Arc A570M by 1.5%, and the AMD Radeon RX 6950 XT by 1.8%. These figures indicate that despite its higher raw score in the direct comparison, the RX 9070 GRE’s benchmark profile places it in a competitive neighborhood populated by older and mid-range parts, whereas the RX 9060 XT LP’s results align it with a slightly stronger peer group.
The single head-to-head result is unambiguous in direction but limited in scope. With only one shared test, the 19.3% delta in favor of the RX 9070 GRE tells a clear story about compute throughput under OpenCL, but it leaves questions about gaming performance, ray tracing, and power efficiency unanswered by direct comparison. The available data does, however, reveal consistent architectural trends that explain the score gap.
Architecture Differences
Both cards share the same RDNA 4.0 architecture and are built on TSMC’s 4 nm process node, yet they diverge substantially in silicon scale. The RX 9060 XT LP uses the Navi 44 chip, which packs 29,700 million transistors onto a 199 mm² die, yielding a transistor density of 149.2 million per square millimeter. The RX 9070 GRE employs the Navi 48 chip, with 53,900 million transistors on a 357 mm² die, achieving a slightly higher density of 151.0 million per square millimeter. The RX 9070 GRE’s die is roughly 79% larger by area and carries about 81% more transistors, which explains its higher compute capacity.
The execution resources scale accordingly. The RX 9070 GRE fields 3,072 shading units, 192 texture mapping units, and 96 raster operation units, compared to the RX 9060 XT LP’s 2,048 shaders, 128 TMUs, and 64 ROPs. Ray tracing hardware follows the same pattern: the RX 9070 GRE includes 48 RT cores versus 32 on the RX 9060 XT LP. Neither card features tensor cores, a notable omission for AI-accelerated workloads.
Clock speeds tell a more nuanced story. The RX 9060 XT LP runs a base clock of 1380 MHz, a game clock of 2450 MHz, and a boost clock of 3050 MHz. The RX 9070 GRE counters with a higher base of 1420 MHz but lower game and boost figures of 2220 MHz and 2790 MHz respectively. Despite the lower boost ceiling, the RX 9070 GRE’s larger shader count produces dramatically higher throughput. Its FP32 performance reaches 34.28 TFLOPS, against 24.99 TFLOPS for the RX 9060 XT LP. FP16 performance mirrors FP32 at a 1:1 ratio for both cards.
Memory configurations diverge in capacity and bandwidth. The RX 9060 XT LP offers 16 GB of GDDR6 on a 128-bit bus, running at 2518 MHz (20.1 Gbps effective) for 322.3 GB/s of bandwidth. The RX 9070 GRE provides 12 GB of GDDR6 on a wider 192-bit bus, at a lower 2250 MHz (18 Gbps effective), yet achieves 432.0 GB/s due to the wider interface. The RX 9060 XT LP thus prioritizes capacity for large datasets, while the RX 9070 GRE emphasizes raw bandwidth.
Other differences emerge in power delivery and connectivity. The RX 9060 XT LP is rated at 140 W TDP with a single 8-pin connector and a 300 W suggested PSU. The RX 9070 GRE draws 220 W, requires two 8-pin connectors, and suggests a 550 W PSU. Both are dual-slot cards with PCIe 5.0 x16 interfaces. Display outputs differ slightly: the RX 9060 XT LP has one HDMI 2.1b and two DisplayPort 2.1a outputs, while the RX 9070 GRE offers one HDMI 2.1b and three DisplayPort 2.1a. API support is identical, with DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
FAQ
Q: Which card has the higher average benchmark score?
A: The AMD Radeon RX 9060 XT LP averages 63,830 across its benchmarks, while the AMD Radeon RX 9070 GRE averages 57,367. The RX 9060 XT LP also ranks higher in the overall GPU percentile at 89th versus 87th.
Q: How large is the performance gap in the direct head-to-head test?
A: In the Geekbench OpenCL test, the RX 9070 GRE scores 109,309 against the RX 9060 XT LP’s 88,183, a 19.3% advantage for the RX 9070 GRE.
Q: Does the RX 9060 XT LP have more memory than the RX 9070 GRE?
A: Yes. The RX 9060 XT LP ships with 16 GB of GDDR6, while the RX 9070 GRE carries 12 GB. However, the RX 9070 GRE’s 192-bit bus delivers 432.0 GB/s of bandwidth versus 322.3 GB/s for the RX 9060 XT LP.
Q: What are the transistor counts for each card?
A: The RX 9060 XT LP uses the Navi 44 chip with 29,700 million transistors on a 199 mm² die. The RX 9070 GRE uses the Navi 48 chip with 53,900 million transistors on a 357 mm² die.
Q: Which card requires more power from the PSU?
A: The RX 9070 GRE has a 220 W TDP and recommends a 550 W PSU, while the RX 9060 XT LP has a 140 W TDP and recommends a 300 W PSU.
Q: Do both cards support the same graphics APIs?
A: Yes, both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. They also share the same RDNA 4.0 architecture and 4 nm process node.
The Verdict
The data presents a clear split between raw compute capability and overall benchmark consistency. The RX 9070 GRE wins the only direct comparison by 19.3%, and its larger silicon footprint — 53,900 million transistors, 3,072 shaders, 34.28 TFLOPS FP32 — makes it the stronger choice for compute-heavy workloads that scale with shading units and memory bandwidth. Its 432.0 GB/s bandwidth and 96 ROPs also suggest better rasterization throughput in memory-bound scenarios.
The RX 9060 XT LP, however, posts a higher average benchmark score and a better percentile ranking. Its 16 GB frame buffer doubles as a practical advantage for large textures or datasets, and its 140 W TDP with a single 8-pin connector makes it far easier to integrate into compact builds. The lower power draw and smaller die size (199 mm² versus 357 mm²) point to a card designed for efficiency-conscious users who still want RDNA 4.0 features.
For a buyer prioritizing maximum compute performance in a traditional ATX chassis, the RX 9070 GRE’s 19.3% lead in OpenCL and its superior texture and pixel rates make it the logical pick. For someone constrained by power supply headroom or physical space, the RX 9060 XT LP’s 16 GB capacity and lower system demands are persuasive. The RX 9070 GRE launched with an MSRP of 549 USD; the RX 9060 XT LP has no listed launch price, so direct cost comparison is not possible from the data.
Specification Differences
| Specification | RX 9060 XT LP | RX 9070 GRE |
|---|---|---|
| Chip | Navi 44 | Navi 48 |
| Transistors | 29,700 million | 53,900 million |
| Die Size | 199 mm² | 357 mm² |
| Transistor Density | 149.2M / mm² | 151.0M / mm² |
| Base Clock | 1380 MHz | 1420 MHz |
| Boost Clock | 3050 MHz | 2790 MHz |
| Game Clock | 2450 MHz | 2220 MHz |
| Memory Clock | 2518 MHz (20.1 Gbps) | 2250 MHz (18 Gbps) |
| Memory Size | 16 GB | 12 GB |
| Memory Bus | 128 bit | 192 bit |
| Memory Bandwidth | 322.3 GB/s | 432.0 GB/s |
| Shading Units | 2048 | 3072 |
| TMUs | 128 | 192 |
| ROPs | 64 | 96 |
| RT Cores | 32 | 48 |
| Pixel Rate | 195.2 GPixel/s | 267.8 GPixel/s |
| Texture Rate | 390.4 GTexel/s | 535.7 GTexel/s |
| FP32 | 24.99 TFLOPS | 34.28 TFLOPS |
| FP16 | 24.99 TFLOPS (1:1) | 34.28 TFLOPS (1:1) |
| TDP | 140 W | 220 W |
| Power Connectors | 1x 8-pin | 2x 8-pin |
| Suggested PSU | 300 W | 550 W |
| Display Outputs | 1x HDMI 2.1b, 2x DP 2.1a | 1x HDMI 2.1b, 3x DP 2.1a |
| Release Date | 2025-12-16 | 2025-05-07 |
| Launch MSRP | None listed | 549 USD |
Where Each One Wins
The RX 9070 GRE wins in every category that measures raw throughput. Its FP32 output of 34.28 TFLOPS is 37% higher than the RX 9060 XT LP’s 24.99 TFLOPS, and its texture rate of 535.7 GTexel/s exceeds the 390.4 GTexel/s of the smaller card. Pixel rate favors the RX 9070 GRE as well, at 267.8 GPixel/s versus 195.2 GPixel/s. The 192-bit memory bus delivers 34% more bandwidth, which benefits high-resolution rendering and compute tasks that stream large data sets. The additional 16 RT cores give it a structural advantage in ray-traced workloads, though no direct ray tracing benchmark appears in the data.
The RX 9060 XT LP wins on efficiency and capacity. Its 140 W TDP is 36% lower than the RX 9070 GRE’s 220 W, and its 300 W suggested PSU is substantially less demanding than the 550 W recommendation for the larger card. The 16 GB frame buffer is 33% larger, which matters for workloads that exceed 12 GB of usage. Its higher boost clock of 3050 MHz suggests better single-threaded or lightly-threaded performance, though the lower shader count limits overall throughput. The RX 9060 XT LP also holds the edge in benchmark consistency, as reflected in its higher average score and percentile ranking.
In practical terms, the RX 9070 GRE is the compute monster, suited for users who need maximum FP32, texture, and pixel throughput and can accommodate its dual 8-pin power requirement. The RX 9060 XT LP is the balanced alternative, offering more memory, lower power demands, and a better overall benchmark average, making it suitable for compact builds or systems with modest PSUs. The choice hinges on whether raw speed or system integration matters more.