NVIDIA CMP 30HX vs NVIDIA GeForce RTX 4090 Mobile Comparison

Head-to-Head Benchmarks

The benchmark data paints an unambiguous picture: the NVIDIA GeForce RTX 4090 Mobile dominates the NVIDIA CMP 30HX in every recorded test. The head-to-head results include only two benchmark comparisons, both from the Geekbench suite, and the RTX 4090 Mobile wins both decisively.

In Geekbench OpenCL, the RTX 4090 Mobile scores 180,831 against the CMP 30HX's 65,199. That is a delta of 63.9% in favor of the RTX 4090 Mobile, meaning the laptop GPU delivers nearly three times the raw compute throughput in this workload. The Vulkan test tells a similar story: the RTX 4090 Mobile records 170,774 points while the CMP 30HX manages 62,484, a 63.4% advantage for the newer part.

The CMP 30HX has zero wins in the recorded head-to-head data, while the RTX 4090 Mobile takes both. The average benchmark score for the CMP 30HX sits at 63,842, which places it at the 89th percentile among all GPUs in the database. The RTX 4090 Mobile's average score is lower at 43,667, but this figure is dragged down by additional benchmark entries, including Passmark tests for DirectX 9, 10, 11, 12, and 2D workloads, which are not present for the CMP 30HX. The RTX 4090 Mobile sits at the 84th percentile.

Context from the nearest rivals is useful. The CMP 30HX's average score of 63,842 is essentially tied with the AMD Radeon RX 9060 XT LP at 63,830, the AMD Radeon RX 7600M at 63,775, and the AMD Radeon Pro Vega 56 at 63,693, with deltas of 0%, 0.1%, and 0.2% respectively. It trails the AMD Radeon Pro WX 9100 by 0.6%. The RTX 4090 Mobile's average of 43,667 puts it within 0.8% of the NVIDIA Quadro M6000, 0.9% of the NVIDIA GeForce RTX 5050 Mobile, and 0.9% of the NVIDIA Quadro M6000 24 GB, while the NVIDIA RTX A6000 leads it by 0.9%.

Architecture Differences

The two GPUs come from different architectural generations and target entirely different use cases. The CMP 30HX is built on the TU116 chip, part of NVIDIA's Turing architecture, manufactured on a 12 nm process at TSMC. It packs 6,600 million transistors into a die size of 284 mm², yielding a transistor density of 23.2 million per square millimeter. The RTX 4090 Mobile uses the AD103 chip from the Ada Lovelace architecture, also produced by TSMC but on a 5 nm node. This part contains 45,900 million transistors on a 379 mm² die, giving a density of 121.1 million per square millimeter. The density difference is stark: Ada Lovelace crams over five times more transistors per area than Turing.

Core counts follow the same pattern. The CMP 30HX has 1,408 shading units, 88 texture mapping units, and 48 raster output units. The RTX 4090 Mobile offers 9,728 shading units, 304 TMUs, and 112 ROPs. That represents a 6.9x increase in shading units, a 3.5x increase in TMUs, and a 2.3x increase in ROPs. The RTX 4090 Mobile also adds dedicated hardware absent from the CMP 30HX: 76 ray tracing cores and 304 tensor cores. The CMP 30HX has no recorded ray tracing or tensor core count.

Clock speeds are closer than the core counts might suggest. The CMP 30HX runs at a base clock of 1530 MHz and boosts to 1785 MHz. The RTX 4090 Mobile has a lower base of 1335 MHz but boosts to 1695 MHz. The CMP 30HX actually has a higher boost clock by 90 MHz, yet the massive core advantage of the RTX 4090 Mobile overwhelms this in every workload. Memory clocks differ substantially: the CMP 30HX uses 1750 MHz memory with 14 Gbps effective data rate, while the RTX 4090 Mobile runs at 2250 MHz with 18 Gbps effective.

Memory capacity and bandwidth also favor the RTX 4090 Mobile. The CMP 30HX has 6 GB of GDDR6 on a 192-bit bus for 336.0 GB/s of bandwidth. The RTX 4090 Mobile has 16 GB of GDDR6 on a 256-bit bus for 576.0 GB/s. That is a 71.4% bandwidth advantage for the newer GPU. Pixel rate is 85.68 GPixel/s for the CMP 30HX versus 189.8 GPixel/s for the RTX 4090 Mobile, and texture rate is 157.1 GTexel/s versus 515.3 GTexel/s. FP32 compute is 5.027 TFLOPS for the CMP 30HX and 32.98 TFLOPS for the RTX 4090 Mobile, a 6.6x difference. FP16 performance also diverges: the CMP 30HX delivers 10.05 TFLOPS at a 2:1 ratio, while the RTX 4090 Mobile achieves 32.98 TFLOPS at 1:1.

Power and physical design reflect their divergent purposes. The CMP 30HX is a dual-slot card rated at 125 W TDP, requiring a single 8-pin power connector and a 300 W suggested power supply. It has no display outputs, a PCIe 1.0 x4 bus interface, and dimensions of 229 mm length, 111 mm height, and 35 mm width. The RTX 4090 Mobile is an integrated graphics package for laptops, rated at 120 W TDP with no power connectors and no fixed dimensions. Its bus interface is PCIe 4.0 x16, and display outputs are listed as portable device dependent.

API support differs as well. The CMP 30HX supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The RTX 4090 Mobile supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Production status also separates them: the CMP 30HX is end-of-life, released on February 24, 2021, while the RTX 4090 Mobile is active, released on January 2, 2023, with the GeForce 30 Mobile as predecessor and GeForce 50 Mobile as successor.

Where Each One Wins

The CMP 30HX was designed for cryptocurrency mining, not general graphics work. Its lack of display outputs makes that explicit. In the recorded benchmarks, it does not win any test against the RTX 4090 Mobile. Its strengths, if any, lie outside the measured workloads: it draws 125 W versus 120 W for the RTX 4090 Mobile, a negligible difference, and its dual-slot desktop form factor with an 8-pin connector makes it easier to install in a standard desktop system than a mobile IGP. Its launch MSRP was 799 USD, which the database records, though no comparable figure exists for the RTX 4090 Mobile.

The RTX 4090 Mobile wins every head-to-head benchmark and does so by massive margins. In OpenCL, its 180,831 score is 2.8x the CMP 30HX's 65,199. In Vulkan, its 170,774 score is 2.7x the CMP 30HX's 62,484. The ray tracing cores and tensor cores present only in the RTX 4090 Mobile suggest advantages in ray-traced workloads and AI-accelerated tasks, though no direct benchmark data in the database confirms this. The 16 GB memory capacity versus 6 GB also positions the RTX 4090 Mobile for larger datasets and higher-resolution textures.

For gaming, the RTX 4090 Mobile is the clear choice. Its DirectX 12 Ultimate support, higher bandwidth, and vastly superior compute make it suitable for modern titles. The CMP 30HX, with no display outputs, cannot drive a monitor at all. For compute workloads, the RTX 4090 Mobile's 32.98 TFLOPS FP32 and 32.98 TFLOPS FP16 at 1:1 ratio dwarf the CMP 30HX's 5.027 TFLOPS FP32 and 10.05 TFLOPS FP16 at 2:1. The CMP 30HX's only conceivable advantage is its desktop form factor and the fact that it is a dedicated mining product, but the data shows no workload where it outperforms the RTX 4090 Mobile.

The Verdict

The data is unambiguous: the NVIDIA GeForce RTX 4090 Mobile is the superior product in every measured category. It wins both head-to-head tests with deltas of 63.9% and 63.4%, offers over six times the shading units, nearly double the memory bandwidth, and a 6.6x advantage in FP32 compute. The CMP 30HX, an end-of-life mining GPU from 2021, cannot compete with the 2023 mobile flagship in any benchmark the database records.

Buyers should note the context. The CMP 30HX is a desktop card with no display outputs, designed exclusively for mining, and it is no longer in production. Its 799 USD launch MSRP reflects that specialized positioning. The RTX 4090 Mobile is an active, current-generation laptop GPU with full display support, ray tracing hardware, and tensor cores. It also runs at a slightly lower TDP of 120 W versus 125 W, making it more power-efficient per unit of performance.

For anyone choosing between these two, the RTX 4090 Mobile is the only sensible option for gaming, content creation, or general compute. The CMP 30HX has no use case in the recorded data where it wins. Its only potential advantage would be in mining-specific workloads, but the database contains no mining benchmarks. The verdict is straightforward: the RTX 4090 Mobile wins on every metric, in every test, and for every purpose the data can evaluate.

FAQ

Q: Which GPU has the higher average benchmark score?

A: The NVIDIA CMP 30HX has an average benchmark score of 63,842, while the NVIDIA GeForce RTX 4090 Mobile has an average of 43,667. However, the RTX 4090 Mobile has additional Passmark benchmark entries that lower its average, and it wins both head-to-head Geekbench tests.

Q: How big is the performance gap in the head-to-head tests?

A: The RTX 4090 Mobile leads by 63.9% in Geekbench OpenCL (180,831 vs 65,199) and by 63.4% in Geekbench Vulkan (170,774 vs 62,484).

Q: What are the memory specifications of each GPU?

A: The CMP 30HX has 6 GB of GDDR6 on a 192-bit bus with 336.0 GB/s bandwidth. The RTX 4090 Mobile has 16 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth.

Q: Does the CMP 30HX support ray tracing?

A: No. The CMP 30HX has no recorded ray tracing cores or tensor cores. The RTX 4090 Mobile has 76 ray tracing cores and 304 tensor cores.

Q: What is the difference in FP32 compute performance?

A: The CMP 30HX delivers 5.027 TFLOPS FP32, while the RTX 4090 Mobile delivers 32.98 TFLOPS FP32, a 6.6x advantage for the RTX 4090 Mobile.

Q: Which GPU is still in production?

A: The RTX 4090 Mobile is listed as active, released on January 2, 2023. The CMP 30HX is end-of-life, released on February 24, 2021, and its launch MSRP was 799 USD.