AMD Radeon 890M vs NVIDIA GeForce RTX 4060 AD106 Comparison

FAQ

Q: Which GPU has the higher average benchmark score in the database?

A: The AMD Radeon 890M has an average benchmark score of 9210, while the NVIDIA GeForce RTX 4060 AD106 has no recorded average benchmark score in the database. The 890M sits at the 45th percentile among all GPUs, whereas the RTX 4060 AD106 sits at the 50th percentile.

Q: What are the transistor counts for these two chips?

A: The AMD Radeon 890M uses a Strix Point chip with 34,000 million transistors on a 233 mm² die. The NVIDIA GeForce RTX 4060 AD106 uses an AD106 chip with 22,900 million transistors on a 188 mm² die.

Q: How do their shading unit counts compare?

A: The NVIDIA GeForce RTX 4060 AD106 has 3072 shading units, which is triple the 1024 shading units found on the AMD Radeon 890M.

Q: What is the memory configuration difference?

A: The AMD Radeon 890M uses system shared memory with a system-dependent bandwidth, while the NVIDIA GeForce RTX 4060 AD106 has 8 GB of dedicated GDDR6 memory on a 128-bit bus with 272.0 GB/s bandwidth.

Q: Both support DirectX 12 Ultimate. Is that correct?

A: Yes, both GPUs list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4 in their API support.

Q: What is the power draw difference?

A: The AMD Radeon 890M has a TDP of 15 W and requires no power connectors, while the NVIDIA GeForce RTX 4060 AD106 has a TDP of 115 W and uses a single 12-pin power connector with a suggested PSU of 300 W.

Architecture Differences

The AMD Radeon 890M and NVIDIA GeForce RTX 4060 AD106 represent fundamentally different design philosophies. The 890M is an integrated graphics processor built on the RDNA 3.5 architecture, part of the Navi III IGP family for Strix Point mobile platforms. It uses a 4 nm process at TSMC, accommodating 34,000 million transistors on a 233 mm² die, yielding a transistor density of 145.9 million transistors per square millimeter. The RTX 4060 AD106, by contrast, is a discrete GeForce 40-series part based on the Ada Lovelace architecture. It uses a 5 nm TSMC process with 22,900 million transistors on a smaller 188 mm² die, resulting in a lower transistor density of 121.8 million per square millimeter.

The compute pipelines diverge sharply. The 890M packs 1024 shading units, 64 texture mapping units, and 32 ROPs, accompanied by 16 ray tracing cores. The RTX 4060 AD106 scales that up to 3072 shading units, 96 TMUs, 48 ROPs, and 24 ray tracing cores. Additionally, the NVIDIA part includes 96 tensor cores, a feature entirely absent from the AMD integrated GPU. These structural differences explain the large gap in raw throughput: the 890M delivers 5.939 TFLOPS of FP32 compute, while the RTX 4060 AD106 delivers 15.11 TFLOPS, roughly 2.5 times higher.

The memory subsystem is another defining architectural split. The 890M relies on system shared memory, with its bus width, type, and bandwidth all dependent on the host platform. The RTX 4060 AD106 uses 8 GB of dedicated GDDR6 memory clocked at 2125 MHz (17 Gbps effective) across a 128-bit interface, producing 272.0 GB/s of bandwidth. This dedicated memory allocation avoids the contention and latency penalties inherent to shared memory designs.

Clock behavior also differs. The 890M has a base clock of 400 MHz and a boost clock of 2900 MHz, a wide dynamic range typical of integrated parts that scale aggressively based on thermal and power headroom. The RTX 4060 AD106 runs at a base of 1830 MHz with a boost of 2460 MHz, reflecting its fixed power envelope of 115 W. The AMD part draws just 15 W and uses no external power connectors, while the NVIDIA part requires a dual-slot cooler, a single 12-pin connector, and a 300 W suggested PSU.

Both chips support PCIe 4.0 x8 interfaces. The 890M is marked as Active in production status, while the RTX 4060 AD106 is listed as End-of-life, with the GeForce 50 as its successor. The 890M carries a release date of 2024-07-14 and has the Navi II IGP as its predecessor; the RTX 4060 AD106 was released on 2024-03-31 with the GeForce 30 as its predecessor.

Where Each One Wins

The benchmark data positions the AMD Radeon 890M as a capable integrated solution that competes with older discrete graphics cards. Its average benchmark score of 9210 places it at the 45th percentile of all GPUs, and its nearest rivals include the AMD Radeon Vega 8 (9221, 0.1% ahead), the NVIDIA GeForce GTX 960 (9273, 0.7% ahead), the NVIDIA GeForce GTX 465 (9294, 0.9% ahead), and the NVIDIA GeForce GTX 850M (9302, 1.0% ahead). This clustering indicates the 890M sits in a performance tier historically occupied by mid-range discrete GPUs from several generations ago, an impressive result for a 15 W integrated part. Its strongest measured results come in compute-oriented workloads: 37,254 in Geekbench OpenCL and 40,808 in Geekbench Vulkan, with a Passmark GPU Compute score of 4157.

The NVIDIA GeForce RTX 4060 AD106 has no recorded benchmark scores in the database, so direct numerical comparisons are not possible from the measurements available. Its 50th percentile ranking and the absence of any head-to-head results mean the analysis must rely on architectural specifications. The RTX 4060 AD106 clearly wins on paper in every compute and rendering resource category: triple the shading units, more TMUs and ROPs, more ray tracing cores, and dedicated tensor cores. Its 15.11 TFLOPS FP32 throughput and 272.0 GB/s memory bandwidth would place it well above the 890M's 5.939 TFLOPS and system-dependent bandwidth in any standard GPU workload. The pixel rate of 118.1 GPixel/s and texture rate of 236.2 GTexel/s for the NVIDIA part are both higher than the 890M's 92.80 GPixel/s and 185.6 GTexel/s.

The practical use-case split is therefore clear. The 890M wins in scenarios requiring minimal power draw, no discrete card installation, and system-level integration. Its 15 W TDP and lack of power connectors make it suitable for thin-and-light mobile devices where the RTX 4060 AD106's 115 W TDP and dual-slot footprint would be impractical. The RTX 4060 AD106 wins in scenarios demanding maximum frame rates, ray tracing performance, and AI-accelerated workloads, where its 3072 shading units, 24 RT cores, and 96 tensor cores provide substantial advantages. The 890M's performance ceiling, as indicated by its Passmark DirectX 9 score of 97 and DirectX 11 score of 73, shows it handles legacy APIs adequately, but its DirectX 12 score of 37 and 3DMark Steel Nomad DX12 score of 590 suggest modern titles will stress its resources.

Specification Differences

| Specification | AMD Radeon 890M | NVIDIA GeForce RTX 4060 AD106 |

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

| Architecture | RDNA 3.5 | Ada Lovelace |

| Generation | Navi III IGP (Strix Point Mobile) | GeForce 40 |

| Process Node | 4 nm | 5 nm |

| Transistors | 34,000 million | 22,900 million |

| Die Size | 233 mm² | 188 mm² |

| Transistor Density | 145.9M / mm² | 121.8M / mm² |

| Base Clock | 400 MHz | 1830 MHz |

| Boost Clock | 2900 MHz | 2460 MHz |

| Memory Size | System Shared | 8 GB |

| Memory Type | System Shared | GDDR6 |

| Memory Bus Width | System Shared | 128 bit |

| Memory Bandwidth | System Dependent | 272.0 GB/s |

| Shading Units | 1024 | 3072 |

| TMUs | 64 | 96 |

| ROPs | 32 | 48 |

| RT Cores | 16 | 24 |

| Tensor Cores | None | 96 |

| Pixel Rate | 92.80 GPixel/s | 118.1 GPixel/s |

| Texture Rate | 185.6 GTexel/s | 236.2 GTexel/s |

| FP32 | 5.939 TFLOPS | 15.11 TFLOPS |

| FP16 | 5.939 TFLOPS (1:1) | 15.11 TFLOPS (1:1) |

| TDP | 15 W | 115 W |

| Slot Width | IGP | Dual-slot |

| Power Connectors | None | 1x 12-pin |

| Suggested PSU | None | 300 W |

| Display Outputs | Portable Device Dependent | 1x HDMI 2.13x DisplayPort 1.4a |

| Production Status | Active | End-of-life |

| Release Date | 2024-07-14 | 2024-03-31 |

| Predecessor | Navi II IGP | GeForce 30 |

| Successor | None | GeForce 50 |

The two GPUs share identical API support: both list DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both use a PCIe 4.0 x8 bus interface. Neither has recorded dimensions for length, height, or width, and neither has a launch MSRP in the database.

Head-to-Head Benchmarks

The database contains no head-to-head benchmark entries for these two GPUs, and the NVIDIA GeForce RTX 4060 AD106 has an empty benchmark array. The only quantitative comparison available comes from the AMD Radeon 890M's individual benchmark scores and its nearest rival list, which does not include the RTX 4060 AD106.

The 890M's recorded scores span multiple testing methodologies. In 3DMark Steel Nomad DX12, it scores 590. Geekbench results show 37,254 in OpenCL and 40,808 in Vulkan. Passmark results cover several API generations: DirectX 9 at 97, DirectX 10 at 33, DirectX 11 at 73, and DirectX 12 at 37. The Passmark G2D score is 979, G3D is 8076, and GPU Compute is 4157. The average benchmark score across all tests is 9210.

Given the RTX 4060 AD106's lack of recorded scores, the specification sheet becomes the basis for expected performance. The NVIDIA part's FP32 throughput of 15.11 TFLOPS is 2.54 times the 890M's 5.939 TFLOPS. Its texture rate of 236.2 GTexel/s exceeds the 185.6 GTexel/s of the AMD part by roughly 27%. The pixel rate advantage is smaller but still clear: 118.1 GPixel/s versus 92.80 GPixel/s, a 27% margin. The RTX 4060 AD106 also has 50% more TMUs (96 versus 64), 50% more ROPs (48 versus 32), 50% more ray tracing cores (24 versus 16), and three times the shading units (3072 versus 1024). Its dedicated 272.0 GB/s memory bandwidth eliminates the system-dependent variable that constrains the 890M.

The 890M's nearest rivals provide context for its placement. The Vega 8 averages 9221, just 0.1% higher. The GTX 960 averages 9273, 0.7% higher. The GTX 465 averages 9294, 0.9% higher. The GTX 850M averages 9302, 1.0% higher. These margins are all within 1%, indicating the 890M performs within a tight band around these older discrete cards. The RTX 4060 AD106, with its 50th percentile ranking and modern Ada Lovelace architecture, would not appear in this cluster based on its architectural resources alone.

The data indicates the 890M is a well-engineered integrated GPU that delivers competitive performance for its 15 W power class. The RTX 4060 AD106, despite having no benchmark scores recorded, possesses a specification sheet that places it in a substantially higher performance tier. The absence of head-to-head measurements means any direct comparison must rely on the architectural differences, which consistently favor the NVIDIA part in raw throughput, memory bandwidth, and feature count.