AMD Radeon Instinct MI60 vs AMD Radeon RX 9060 XT LP Comparison
AMD Radeon Instinct MI60
Radeon RX 9060 XT LP
PERFORMANCE BENCHMARKS
Analysis: AMD Radeon Instinct MI60 vs AMD Radeon RX 9060 XT LP
Head-to-Head Benchmarks
The benchmark data leaves little room for ambiguity: the AMD Radeon Instinct MI60 dominates the AMD Radeon RX 9060 XT LP in both recorded tests. Out of two head-to-head comparisons, the Instinct MI60 takes both wins, with the most dramatic margin appearing in the Vulkan workload.
In Geekbench OpenCL, the Instinct MI60 scores 92,488 against the RX 9060 XT LP's 88,183. That is a 4.9% advantage for the older accelerator. While the margin is modest, it is consistent with the MI60's placement in the broader database: it sits at the 93rd percentile among all GPUs, whereas the RX 9060 XT LP lands at the 89th percentile. The OpenCL result shows a meaningful but not overwhelming gap, one that suggests the MI60's compute-oriented design still holds up against a much newer, lower-power card.
The Vulkan test tells a very different story. Here the Instinct MI60 scores 92,444, while the RX 9060 XT LP manages only 39,476. That works out to a 134.2% delta in favor of the MI60. This is not a close contest; the MI60 more than doubles the RX 9060 XT LP in Vulkan performance. The RX 9060 XT LP's Vulkan score is so far behind its own OpenCL result that it drags its average benchmark score down to 63,830, compared to the MI60's 92,466 average. The RX 9060 XT LP's average is pulled toward the 89th percentile, but its Vulkan figure is clearly an outlier weakness relative to its OpenCL showing.
The average benchmark scores reinforce the hierarchy. The MI60's average of 92,466 places it among rivals like the NVIDIA RTX A4500 (91,671, a 0.9% gap) and the AMD Radeon Pro VII (97,131, a -4.8% gap). The RX 9060 XT LP's average of 63,830, by contrast, sits near the NVIDIA CMP 30HX (63,842, a 0% delta) and the AMD Radeon RX 7600M (63,775, a 0.1% delta). In other words, the two cards are not just separated by one benchmark result; they occupy entirely different performance tiers in the database. The MI60 competes with professional workstation accelerators, while the RX 9060 XT LP clusters with midrange mobile and mining-oriented parts.
Where Each One Wins
The AMD Radeon Instinct MI60 is the clear winner in compute-heavy workloads, especially those that leverage Vulkan. Its 134.2% Vulkan advantage is the single largest differentiator between the two cards. For applications that rely on Vulkan compute, the MI60 is overwhelmingly faster. Its OpenCL lead of 4.9% is smaller but still decisive, meaning the MI60 also holds an edge in OpenCL-based rendering, scientific simulation, and machine learning inference tasks that use that API.
The AMD Radeon RX 9060 XT LP does not win any recorded benchmark. However, the data suggests where it might be preferable in practical terms. The RX 9060 XT LP has a 140 W TDP versus the MI60's 300 W TDP, and its suggested power supply is 300 W against the MI60's 700 W. It also uses a single 8-pin power connector, while the MI60 requires a 6-pin plus an 8-pin. The RX 9060 XT LP is an active production card, whereas the MI60 is end-of-life. For systems where power delivery, thermals, or availability are constraints, the RX 9060 XT LP is the more practical choice, even though it loses every benchmark comparison.
The MI60 also wins on memory capacity and bandwidth. It offers 32 GB of HBM2 across a 4096-bit bus, delivering 1.02 TB/s of bandwidth. The RX 9060 XT LP has 16 GB of GDDR6 on a 128-bit bus, with 322.3 GB/s of bandwidth. For datasets that exceed 16 GB or workloads that are bandwidth-bound, the MI60's memory subsystem is categorically superior.
Architecture Differences
The two cards come from completely different architectural generations. The AMD Radeon Instinct MI60 uses the Vega 20 chip, built on GCN 5.1 architecture, fabricated on TSMC's 7 nm process. The AMD Radeon RX 9060 XT LP uses the Navi 44 chip, based on RDNA 4.0, on TSMC's 4 nm node. The process node difference is significant: 7 nm versus 4 nm, which partly explains the RX 9060 XT LP's much higher transistor density.
Transistor counts and die sizes diverge sharply. The MI60 packs 13,230 million transistors into a 331 mm² die, yielding a density of 40.0 million transistors per square millimeter. The RX 9060 XT LP crams 29,700 million transistors into a much smaller 199 mm² die, achieving 149.2 million transistors per square millimeter. That is roughly 3.7 times the transistor density, a direct consequence of the newer process node.
Core configurations also differ. The MI60 has 4096 shading units, 256 texture mapping units, and 64 render output units. The RX 9060 XT LP has 2048 shading units, 128 TMUs, and 64 ROPs. The MI60 has double the shaders and TMUs, but the same ROP count. The RX 9060 XT LP, however, includes 32 ray tracing cores, a feature the MI60 lacks entirely. The MI60's FP32 throughput is 14.75 TFLOPS, while the RX 9060 XT LP reaches 24.99 TFLOPS. In FP16, the MI60 hits 29.49 TFLOPS with a 2:1 ratio, while the RX 9060 XT LP delivers 24.99 TFLOPS at a 1:1 ratio.
The memory architectures are fundamentally different as well. The MI60 uses HBM2 with a 4096-bit bus, while the RX 9060 XT LP uses GDDR6 with a 128-bit bus. The MI60's memory clock is 1000 MHz (2 Gbps effective), and the RX 9060 XT LP's memory runs at 2518 MHz (20.1 Gbps effective). The RX 9060 XT LP's memory is much faster per pin, but the MI60's enormous bus width gives it a 1.02 TB/s bandwidth advantage.
Specification Differences
The two cards differ across nearly every major specification category. The MI60 is built on the GCN 5.1 architecture with the Vega 20 chip, while the RX 9060 XT LP uses RDNA 4.0 with the Navi 44 chip. The process node is 7 nm for the MI60 and 4 nm for the RX 9060 XT LP.
The MI60's base clock is 1200 MHz with a boost clock of 1800 MHz. The RX 9060 XT LP has a base clock of 1380 MHz, a game clock of 2450 MHz, and a boost clock of 3050 MHz. Despite the MI60's higher shader count, the RX 9060 XT LP's much higher clocks push its FP32 throughput to 24.99 TFLOPS versus the MI60's 14.75 TFLOPS.
Memory capacity is 32 GB of HBM2 for the MI60 versus 16 GB of GDDR6 for the RX 9060 XT LP. Bus widths are 4096-bit versus 128-bit, and bandwidth is 1.02 TB/s versus 322.3 GB/s. The RX 9060 XT LP has 32 ray tracing cores; the MI60 has none.
Power requirements differ substantially. The MI60 has a 300 W TDP, requires a 700 W power supply, and uses a 6-pin plus an 8-pin connector. The RX 9060 XT LP has a 140 W TDP, requires a 300 W power supply, and uses a single 8-pin connector. Both are dual-slot cards.
The bus interface differs: the MI60 uses PCIe 4.0 x16, while the RX 9060 XT LP uses PCIe 5.0 x16. Display outputs also differ. The MI60 has a single mini-DisplayPort 1.4a output, while the RX 9060 XT LP has one HDMI 2.1b and two DisplayPort 2.1a outputs. The MI60 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.3. The RX 9060 XT LP supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.
The MI60 is end-of-life and was released on 2018-11-17. The RX 9060 XT LP is active and was released on 2025-12-16. The MI60's predecessor is FirePro Data Center, and the RX 9060 XT LP's predecessor is Navi III.
FAQ
Q: Which GPU wins in OpenCL performance?
A: The AMD Radeon Instinct MI60 scores 92,488 in Geekbench OpenCL, beating the AMD Radeon RX 9060 XT LP's 88,183 by 4.9%.
Q: How large is the Vulkan performance gap between the two cards?
A: The MI60 scores 92,444 in Geekbench Vulkan, while the RX 9060 XT LP scores 39,476. The MI60 leads by 134.2%, more than doubling the RX 9060 XT LP's score.
Q: Does the RX 9060 XT LP have any advantage in memory bandwidth?
A: No. The MI60 provides 1.02 TB/s of bandwidth from 32 GB of HBM2 on a 4096-bit bus. The RX 9060 XT LP offers 322.3 GB/s from 16 GB of GDDR6 on a 128-bit bus.
Q: How do the power requirements differ?
A: The MI60 has a 300 W TDP and a suggested 700 W power supply, using a 6-pin plus an 8-pin connector. The RX 9060 XT LP has a 140 W TDP and a suggested 300 W power supply, using a single 8-pin connector.
Q: Which GPU has ray tracing cores?
A: Only the RX 9060 XT LP has ray tracing cores, with 32 of them. The MI60 has no ray tracing cores.
Q: What is the average benchmark score difference?
A: The MI60 has an average benchmark score of 92,466, while the RX 9060 XT LP averages 63,830. The MI60 sits at the 93rd percentile among all GPUs, and the RX 9060 XT LP at the 89th percentile.
The Verdict
The data points to a clear conclusion: the AMD Radeon Instinct MI60 is the superior performer in every recorded benchmark. Its OpenCL lead of 4.9% and Vulkan lead of 134.2% make it the obvious choice for compute workloads that can use either API. Its 32 GB of HBM2 memory with 1.02 TB/s bandwidth further cements its position for large datasets and bandwidth-intensive tasks. The MI60's 93rd percentile ranking, alongside rivals like the NVIDIA RTX A4500 and AMD Radeon Pro VII, confirms that it belongs in the professional accelerator tier.
The AMD Radeon RX 9060 XT LP, by contrast, loses both head-to-head tests and sits in a lower performance tier, with an average score near the NVIDIA CMP 30HX and AMD Radeon RX 7600M. Its strengths are practical rather than performance-based. It draws less than half the power (140 W versus 300 W), requires a much smaller power supply (300 W versus 700 W), and uses a single 8-pin connector. It is also an active product with newer display outputs, including HDMI 2.1b and DisplayPort 2.1a, and it supports Vulkan 1.4 and DirectX 12 Ultimate. Its higher FP32 throughput of 24.99 TFLOPS and higher boost clock of 3050 MHz do not translate into benchmark wins, but they indicate a more modern, efficient design.
Who should pick which? Users whose priority is raw compute performance, especially in Vulkan, should choose the MI60 without hesitation. The same goes for workloads that need more than 16 GB of memory or bandwidth beyond 322.3 GB/s. Users who need a lower-power, actively produced card with modern display outputs and ray tracing support should choose the RX 9060 XT LP, provided they are willing to accept significantly lower benchmark scores. The MI60 is the performance winner; the RX 9060 XT LP is the efficiency and practicality winner. The benchmark data does not support any other conclusion.