AMD Radeon RX 9060 XT LP vs NVIDIA CMP 30HX Comparison

The NVIDIA CMP 30HX and AMD Radeon RX 9060 XT LP are two graphics cards that end up nearly tied in overall average benchmark scores, yet they achieve that parity through wildly different strengths. The CMP 30HX, a Turing-era mining part with no display outputs, posts an average score of 63842, while the RDNA 4.0-based RX 9060 XT LP averages 63830. That 0.0% delta between them in the nearest-rivals data makes this a true split decision, but the underlying benchmark results show two cards that win in completely separate application types.

FAQ

Q: Which card has the higher average benchmark score?

A: The NVIDIA CMP 30HX edges out the AMD Radeon RX 9060 XT LP by a razor-thin margin. The CMP 30HX averages 63842, while the RX 9060 XT LP averages 63830, a difference of just 12 points, which rounds to a 0.0% deltaPct in the nearest-rivals listing.

Q: Which card wins in OpenCL performance?

A: The AMD Radeon RX 9060 XT LP dominates in the Geekbench OpenCL test, scoring 88183 compared to the CMP 30HX's 65199. This represents a 26.1% advantage for the AMD card in that specific workload.

Q: Which card wins in Vulkan performance?

A: The NVIDIA CMP 30HX takes a decisive victory in the Geekbench Vulkan test. It scores 62484 against the RX 9060 XT LP's 39476, giving the NVIDIA card a 58.3% lead in that benchmark.

Q: How do the cards compare in terms of memory capacity?

A: The AMD Radeon RX 9060 XT LP ships with 16 GB of GDDR6 memory, while the NVIDIA CMP 30HX has only 6 GB of GDDR6. Both use GDDR6, but the AMD card offers substantially more capacity.

Q: What are the display output capabilities of each card?

A: The AMD Radeon RX 9060 XT LP has 1x HDMI 2.1b and 2x DisplayPort 2.1a outputs. The NVIDIA CMP 30HX has no display outputs at all, a direct consequence of its mining-focused design.

Q: What is the production status of each card?

A: The NVIDIA CMP 30HX is listed as end-of-life, having been released in 2021. The AMD Radeon RX 9060 XT LP is listed as active, with a release date in late 2025.

Where Each One Wins

The split is clean and stark. The AMD Radeon RX 9060 XT LP wins in compute-heavy, general-purpose workloads as measured by Geekbench OpenCL. Its score of 88183 is far ahead of the CMP 30HX's 65199 in that test. This makes it the clear choice for tasks that lean on raw shader throughput and parallel compute, as the data shows a 26.1% advantage in this area.

The NVIDIA CMP 30HX, conversely, wins decisively in Vulkan-based workloads. Its Geekbench Vulkan score of 62484 crushes the RX 9060 XT LP's 39476, a 58.3% margin. This suggests the older Turing architecture has a significant advantage in driver-level Vulkan optimization or API-specific execution, making it the stronger pick for Vulkan-centric applications.

For overall average performance, the two are inseparable. The CMP 30HX's average of 63842 and the RX 9060 XT LP's 63830 put them within 0.1% of each other, and both sit at the 89th percentile among all GPUs. Anyone choosing between them must prioritize the specific API or workload type, because a generic "which is faster" question has no single answer from the data.

Architecture Differences

The architectural gap between these two is generational. The NVIDIA CMP 30HX uses the TU116 chip built on Turing architecture, manufactured on a 12 nm process at TSMC. It packs 6,600 million transistors into a 284 mm² die, giving a transistor density of 23.2 million per mm². This is an older, larger-node design with no dedicated ray tracing or tensor cores listed in the specs.

The AMD Radeon RX 9060 XT LP uses the Navi 44 chip on RDNA 4.0 architecture, built on a 4 nm process, also at TSMC. It contains 29,700 million transistors in a 199 mm² die, achieving a far higher density of 149.2 million per mm². This card includes 32 ray tracing cores, a feature entirely absent from the CMP 30HX's spec sheet. The difference in process node and transistor density is enormous: the AMD card fits over four times as many transistors into a smaller physical die.

The API support also differs. The CMP 30HX supports DirectX 12 (12_1), while the RX 9060 XT LP supports DirectX 12 Ultimate (12_2). Both offer OpenGL 4.6 and Vulkan 1.4, but the higher DirectX feature level on the AMD card reflects its newer architecture. The bus interface differs as well, with the CMP 30HX using PCIe 1.0 x4 and the RX 9060 XT LP using PCIe 5.0 x16, an enormous difference in potential data transfer bandwidth.

Specification Differences

The specification sheets diverge on nearly every major component. Clock speeds show the AMD card's advantage: it has a base clock of 1380 MHz, a game clock of 2450 MHz, and a boost clock of 3050 MHz. The NVIDIA card has a base of 1530 MHz and a boost of 1785 MHz, but no game clock listed. The AMD card's boost clock is roughly 70% higher than the NVIDIA card's.

Memory configuration differs in capacity and bandwidth. The CMP 30HX has 6 GB of GDDR6 on a 192-bit bus, delivering 336.0 GB/s. The RX 9060 XT LP has 16 GB of GDDR6 on a 128-bit bus, delivering 322.3 GB/s. The AMD card has more capacity but slightly lower bandwidth due to its narrower bus. The effective memory speed is 14 Gbps on the NVIDIA card versus 20.1 Gbps on the AMD card.

Compute unit counts tell a similar story. The CMP 30HX has 1408 shading units, 88 texture mapping units, and 48 raster operation units. The RX 9060 XT LP has 2048 shading units, 128 TMUs, and 64 ROPs. This translates to a massive throughput difference: the AMD card delivers 24.99 TFLOPS of FP32 performance and 195.2 GPixel/s pixel rate, while the NVIDIA card manages 5.027 TFLOPS and 85.68 GPixel/s. The texture rate is 390.4 GTexel/s on AMD versus 157.1 GTexel/s on NVIDIA.

Power and physical specs are closer. The CMP 30HX has a TDP of 125 W, while the RX 9060 XT LP is rated at 140 W. Both use a dual-slot design and a single 8-pin power connector, with a suggested PSU of 300 W. The NVIDIA card measures 229 mm in length, 111 mm in height, and 35 mm in width, while the AMD card's dimensions are not listed. The CMP 30HX has no display outputs, while the RX 9060 XT LP offers HDMI 2.1b and DisplayPort 2.1a.

Head-to-Head Benchmarks

The two benchmark results could not paint a more polarized picture. In Geekbench OpenCL, the AMD Radeon RX 9060 XT LP scores 88183 against the NVIDIA CMP 30HX's 65199. That is a 26.1% delta in favor of the AMD card, and it reflects the raw compute advantage suggested by the FP32 specifications: the RX 9060 XT LP's 24.99 TFLOPS is roughly five times the CMP 30HX's 5.027 TFLOPS. The OpenCL result is the single biggest win for either card.

The Geekbench Vulkan test flips the script entirely. The NVIDIA CMP 30HX scores 62484, while the AMD Radeon RX 9060 XT LP manages only 39476. This gives the NVIDIA card a 58.3% advantage, an even larger margin than the AMD card's OpenCL win. The Vulkan result is surprising given the AMD card's superior theoretical specs, but the data is unambiguous: the CMP 30HX is far faster in this API, suggesting that raw compute specs do not always translate to API-specific performance.

With one win each, the head-to-head is a tie. The average benchmark scores reflect this balance, with the CMP 30HX at 63842 and the RX 9060 XT LP at 63830. The nearest-rivals data confirms the tie, showing the two cards at a 0.0% deltaPct relative to each other, with the AMD Radeon RX 7600M and AMD Radeon Pro Vega 56 both within 0.2% behind and the AMD Radeon Pro WX 9100 only 0.6% ahead.

The Verdict

The data supports a clear split decision. For anyone running Vulkan-based applications, the NVIDIA CMP 30HX is the definitive choice, offering a 58.3% performance advantage in that benchmark over the RX 9060 XT LP. Its average score of 63842 is marginally higher overall, and it holds the edge in the specific API where it wins. However, this card has no display outputs, so it is only viable in systems where video output is handled by another GPU or where it is used purely for compute or mining tasks.

For OpenCL workloads, the AMD Radeon RX 9060 XT LP is the superior card by a 26.1% margin. It also brings 16 GB of memory versus 6 GB, a modern 4 nm process, ray tracing cores, and standard display outputs with HDMI 2.1b and DisplayPort 2.1a. Its 24.99 TFLOPS of FP32 performance dwarfs the CMP 30HX's 5.027 TFLOPS, making it the better tool for general-purpose compute that leverages OpenCL.

The practical verdict depends on the workload. If the task is Vulkan-centric or requires a mining part with no video output, the NVIDIA CMP 30HX wins. If the task involves OpenCL, needs more than 6 GB of memory, or requires display connectivity, the AMD Radeon RX 9060 XT LP is the only sensible pick. The near-identical average scores (63842 vs 63830) and shared 89th percentile ranking mean neither card is categorically faster; they are simply optimized for different APIs. Choose based on the software you actually run, not the overall averages.