AMD Radeon RX 7600M vs NVIDIA GeForce RTX 5090 Mobile Comparison

FAQ

Q: How does the AMD Radeon RX 7600M compare to the NVIDIA GeForce RTX 5090 Mobile in compute performance?

**A: In the only direct head-to-head benchmark, Geekbench OpenCL, the RTX 5090 Mobile scores 201834, which is 68.4% higher than the RX 7600M's 63775. The NVIDIA part wins the sole recorded comparison.

Q: Which GPU has a higher transistor density?

A: The RTX 5090 Mobile packs 120.6M transistors per mm², while the RX 7600M has a density of 65.2M per mm². The NVIDIA chip uses a 5 nm process at TSMC, whereas the AMD part uses a 6 nm process, also at TSMC.

Q: What are the memory capacities of these two mobile GPUs?

A: The RX 7600M has 8 GB of GDDR6 memory on a 128-bit bus with 256.0 GB/s bandwidth. The RTX 5090 Mobile features 24 GB of GDDR7 memory on a 256-bit bus with 896.0 GB/s bandwidth.

Q: How do their rendering rates compare?

A: The RX 7600M has a pixel rate of 154.2 GPixel/s and a texture rate of 269.9 GTexel/s. The RTX 5090 Mobile reaches 169.7 GPixel/s and 496.9 GTexel/s, giving it the edge in both metrics.

Q: Which GPU has more shading units and ray tracing cores?

A: The RTX 5090 Mobile has 10496 shading units and 82 ray tracing cores, while the RX 7600M has 1792 shading units and 28 ray tracing cores. The NVIDIA GPU also includes 328 tensor cores, which the AMD part lacks.

Q: What is the release timeline difference between the two?

A: The RX 7600M launched on January 3, 2023, while the RTX 5090 Mobile launched on March 26, 2025. The AMD part's predecessor is Polaris Mobile, and the NVIDIA GPU's predecessor is GeForce 40 Mobile.

Architecture Differences

The two GPUs come from fundamentally different design generations. The AMD Radeon RX 7600M uses the Navi 33 chip with RDNA 3.0 architecture and the codename "Hotpink Bonefish." It belongs to the Navi Mobile (RX 7000M) generation. The NVIDIA GeForce RTX 5090 Mobile uses the GB203 chip with Blackwell 2.0 architecture and belongs to the GeForce 50 Mobile generation. The manufacturing processes differ: the RX 7600M is built on a 6 nm node at TSMC, while the RTX 5090 Mobile uses a 5 nm node, also at TSMC. This process difference contributes to a significant transistor density gap, 65.2M per mm² versus 120.6M per mm².

The transistor counts tell a similar story. The RX 7600M contains 13,300 million transistors on a die size of 204 mm². The RTX 5090 Mobile houses 45,600 million transistors on a 378 mm² die. That is over three times the transistor count, though the NVIDIA die is less than double the size. The architectural consequences appear in the compute resources. The RX 7600M has 1792 shading units, 112 texture mapping units, 64 ROPs, and 28 ray tracing cores. The RTX 5090 Mobile has 10496 shading units, 328 TMUs, 112 ROPs, and 82 ray tracing cores. It also features 328 tensor cores, a block entirely absent from the AMD specification.

Clock behavior also differs. The RX 7600M runs at a 1500 MHz base clock, 2410 MHz boost, and a 2070 MHz game clock. The RTX 5090 Mobile has a lower 990 MHz base and a 1515 MHz boost, with no game clock listed. Despite lower clocks, the NVIDIA chip achieves higher theoretical throughput. The FP32 compute rating is 17.27 TFLOPS for the RX 7600M versus 31.80 TFLOPS for the RTX 5090 Mobile. The FP16 figures are notable: the AMD GPU doubles its FP32 rate to 34.55 TFLOPS with a 2:1 ratio, while the NVIDIA part holds FP16 at 31.80 TFLOPS with a 1:1 ratio. The memory subsystem is equally divergent. The RX 7600M uses 8 GB of GDDR6 with a 128-bit bus and 256.0 GB/s bandwidth. The RTX 5090 Mobile uses 24 GB of GDDR7 with a 256-bit bus and 896.0 GB/s bandwidth. The NVIDIA part also supports PCIe 5.0 x16, while the AMD part uses PCIe 4.0 x16. Both share the same API support: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are listed as IGP slot width with no power connectors, and both are marked as production status Active.

Head-to-Head Benchmarks

The database contains only one direct comparison between these two GPUs: Geekbench OpenCL. The results are lopsided. The NVIDIA GeForce RTX 5090 Mobile scores 201834, while the AMD Radeon RX 7600M scores 63775. The delta is 68.4% in favor of NVIDIA. This is not a marginal gap; it is a dominant performance separation. The RX 7600M trails by more than two-thirds of its own score. The result is consistent with the raw specification differences. The RTX 5090 Mobile has 5.9 times the shading units, 2.9 times the ray tracing cores, and 3.5 times the memory bandwidth. The OpenCL workload appears to scale strongly with these resources.

The RX 7600M's only recorded benchmark is this same Geekbench OpenCL run, with an average benchmark score of 63775. Its percentile ranking among all GPUs is 89. The nearest rivals provide context: the AMD Radeon RX 9060 XT LP scores 63830 (0.1% ahead), the NVIDIA CMP 30HX scores 63842 (0.1% ahead), the AMD Radeon Pro Vega 56 scores 63693 (0.1% behind), and the AMD Radeon Pro WX 9100 scores 64212 (0.7% ahead). The RX 7600M sits in a tightly packed cluster around 64k. The RTX 5090 Mobile, in contrast, has a broader benchmark profile. Its Geekbench OpenCL score of 201834 is joined by Geekbench Vulkan at 198405, Passmark G3D at 30034, Passmark GPU Compute at 13401, Passmark G2D at 1057, Passmark DirectX 11 at 269, Passmark DirectX 9 at 324, Passmark DirectX 10 at 183, and Passmark DirectX 12 at 138. It also has a 3DMark Steel Nomad DX12 score of 5871. Its average benchmark score is 45152, with a percentile ranking of 84. The percentile difference is small, 89 versus 84, but the underlying scores are vastly different. The RX 7600M holds a higher percentile because its single benchmark is compared against a different distribution, while the RTX 5090 Mobile's average is dragged down by low-scoring legacy DirectX tests. The nearest rivals for the RTX 5090 Mobile include the AMD Radeon Pro 5500 XT at 45384 (0.5% ahead), the NVIDIA GeForce RTX 4070 Ti at 44795 (0.8% behind), the Intel Arc A730M at 45592 (1.0% ahead), and the NVIDIA RTX 5880 Ada Generation at 45972 (1.8% ahead). These rivals cluster around 45k, far below the RTX 5090 Mobile's OpenCL peak.

Specification Differences

| Specification | AMD Radeon RX 7600M | NVIDIA GeForce RTX 5090 Mobile |

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

| Process Node | 6 nm | 5 nm |

| Transistors | 13,300 million | 45,600 million |

| Die Size | 204 mm² | 378 mm² |

| Transistor Density | 65.2M / mm² | 120.6M / mm² |

| Base Clock | 1500 MHz | 990 MHz |

| Boost Clock | 2410 MHz | 1515 MHz |

| Game Clock | 2070 MHz | Not specified |

| Memory Size | 8 GB | 24 GB |

| Memory Type | GDDR6 | GDDR7 |

| Memory Bus | 128 bit | 256 bit |

| Memory Bandwidth | 256.0 GB/s | 896.0 GB/s |

| Memory Clock | 2000 MHz, 16 Gbps effective | 1750 MHz, 28 Gbps effective |

| Shading Units | 1792 | 10496 |

| TMUs | 112 | 328 |

| ROPs | 64 | 112 |

| Ray Tracing Cores | 28 | 82 |

| Tensor Cores | None | 328 |

| Pixel Rate | 154.2 GPixel/s | 169.7 GPixel/s |

| Texture Rate | 269.9 GTexel/s | 496.9 GTexel/s |

| FP32 | 17.27 TFLOPS | 31.80 TFLOPS |

| FP16 | 34.55 TFLOPS (2:1) | 31.80 TFLOPS (1:1) |

| TDP | 90 W | 95 W |

| Bus Interface | PCIe 4.0 x16 | PCIe 5.0 x16 |

| Release Date | 2023-01-03 | 2025-03-26 |

Both GPUs share DirectX 12 Ultimate (12_2), OpenGL 4.6, Vulkan 1.4, IGP slot width, no power connectors, and portable-device-dependent display outputs. Neither has a launch MSRP listed.

Where Each One Wins

The RX 7600M wins in clock speed. Its base clock of 1500 MHz is 510 MHz higher than the RTX 5090 Mobile's 990 MHz, and its boost of 2410 MHz is 895 MHz higher than the NVIDIA part's 1515 MHz. The game clock of 2070 MHz is a feature the RTX 5090 Mobile does not list at all. The AMD GPU also wins in FP16 throughput relative to its own FP32 rate, with a 2:1 ratio producing 34.55 TFLOPS, whereas the NVIDIA GPU's FP16 is capped at its FP32 value of 31.80 TFLOPS. For workloads that use FP16 arithmetic, the RX 7600M offers a higher raw figure despite its lower overall compute.

The RTX 5090 Mobile wins in nearly every other measurable category. It has 3.2 times the shading units, 2.9 times the TMUs, 1.75 times the ROPs, and 2.9 times the ray tracing cores. It is the only one of the two with tensor cores. Its FP32 compute is 31.80 TFLOPS versus 17.27 TFLOPS, an 84% advantage. Its memory bandwidth is 896.0 GB/s versus 256.0 GB/s, a 3.5 times advantage. Its pixel rate is 169.7 GPixel/s versus 154.2 GPixel/s, and its texture rate is 496.9 GTexel/s versus 269.9 GTexel/s. The Geekbench OpenCL result reflects all of this: the RTX 5090 Mobile wins the only head-to-head test by 68.4%.

The Verdict

The data points to a clear separation in capability. The NVIDIA GeForce RTX 5090 Mobile is the stronger GPU for compute-heavy tasks, ray tracing, and high-resolution memory workloads. Its 24 GB of GDDR7 memory, 896.0 GB/s bandwidth, 10496 shading units, and 82 ray tracing cores place it in a different performance class from the RX 7600M. The single recorded benchmark, Geekbench OpenCL, shows a 68.4% margin in favor of NVIDIA. The RTX 5090 Mobile also has tensor cores, which the RX 7600M does not, making it the only option here for workloads that leverage tensor acceleration.

The AMD Radeon RX 6100M is not without merits. It draws 90 W TDP, only 5 W less than the RTX 5090 Mobile, yet delivers its performance with far fewer resources. It holds higher clock speeds across base, boost, and game clocks, and it has a higher FP16 throughput of 34.55 TFLOPS. In the narrow context of FP16 compute, it outperforms the RTX 5090 Mobile's 31.80 TFLOPS. For users who prioritize FP16-heavy workloads, the RX 7600M could be the relevant choice. Its higher percentile ranking of 89 versus 84 also suggests that, relative to the entire GPU database distribution, the RX 7600M punches above its weight.

For buyers choosing between an older RX 7000-series mobile GPU and a newer Blackwell 2.0 mobile GPU, the choice depends on workload. The RTX 5090 Mobile is the clear winner for general compute, memory bandwidth, ray tracing, and tensor operations. The RX 7600M is the pick for FP16 compute and for users who want a lower transistor count, smaller die, and higher clocks. The benchmark data, however, is unambiguous: the RTX 5090 Mobile wins the only direct test, and wins it by a wide margin.