AMD Radeon 890M vs AMD Radeon AI PRO 9600D Comparison

Head-to-Head Benchmarks

The database contains no direct head-to-head benchmark comparisons between the AMD Radeon 890M and the AMD Radeon AI PRO 9600D. The head-to-head benchmark array is empty, and neither part records wins in a direct matchup. The 890M, however, has an extensive set of recorded benchmark scores, while the AI PRO 9600D has no benchmark entries at all in the current data.

For the AMD Radeon 890M, the recorded data shows a 3DMark Steel Nomad DX12 score of 590, a Geekbench OpenCL score of 37254, and a Geekbench Vulkan score of 40808. The PassMark suite shows DirectX 10 performance at 33, DirectX 11 at 73, DirectX 12 at 37, and DirectX 9 at 97. The 2D graphics score is 979, the 3D graphics score is 8076, and the GPU compute score is 4157. The average benchmark score across all recorded tests is 9210, placing it in the 45th percentile of all GPUs.

The nearest rivals to the 890M, based on average score, are the AMD Radeon Vega 8 with an average score of 9221 and a delta of -0.1%, the NVIDIA GeForce GTX 960 at 9273 with a -0.7% delta, the NVIDIA GeForce GTX 465 at 9294 with a -0.9% delta, and the NVIDIA GeForce GTX 850M at 9302 with a -1% delta. These deltas are all negative, meaning the 890M sits slightly below each of these rivals in average score. The margin is extremely tight, with the closest rival, the Vega 8, only 0.1% ahead. This indicates the 890M operates in a performance band nearly identical to these older discrete graphics solutions.

The AI PRO 9600D shows an average benchmark score of 0 and a 50th percentile ranking, with no recorded test scores and no nearest rivals listed. The absence of data means no direct numerical comparison can be drawn from the benchmark suite. The percentile field of 50 for the AI PRO 9600D is based on its specification positioning rather than measured results, while the 890M's 45th percentile stems from its actual recorded scores.

Architecture Differences

The two GPUs diverge sharply at the architectural level. The AMD Radeon 890M uses the Strix Point chip built on the RDNA 3.5 architecture, part of the Navi III IGP generation for Strix Point Mobile. The AMD Radeon AI PRO 9600D uses the Navi 48 chip on the newer RDNA 4.0 architecture, from the Radeon Pro Navi generation under the Navi IV series. Both are manufactured on a 4 nm process at TSMC, but the transistor counts and die sizes differ substantially.

The 890M integrates 34,000 million transistors on a 233 mm² die, yielding a transistor density of 145.9M per mm². The AI PRO 9600D packs 53,900 million transistors on a 357 mm² die, with a density of 151.0M per mm². The AI PRO 9600D therefore carries roughly 58% more transistors and a larger physical die, while also achieving a slightly higher transistor density.

Clock speeds show a notable split. The 890M has a base clock of 400 MHz and a boost clock of 2900 MHz. The AI PRO 9600D has a base clock of 1080 MHz, a boost clock of 2020 MHz, and a game clock of 1080 MHz. The 890M boosts significantly higher, but the AI PRO 9600D operates at a much higher base frequency. Memory clocks differ as well: the 890M uses system shared memory with no dedicated clock, while the AI PRO 9600D runs its memory at 2250 MHz with 18 Gbps effective.

The shading and compute resources are heavily skewed toward the AI PRO 9600D. It contains 3072 shading units, 192 texture mapping units, 96 raster operation units, and 48 ray tracing cores. The 890M has 1024 shading units, 64 TMUs, 32 ROPs, and 16 ray tracing cores. The AI PRO 9600D triples the shading units, triples ROPs, and triples ray tracing cores, while offering three times the TMUs.

Pixel and texture rates reflect this resource advantage. The AI PRO 9600D posts a pixel rate of 193.9 GPixel/s and a texture rate of 387.8 GTexel/s, compared to the 890M's 92.80 GPixel/s and 185.6 GTexel/s. FP32 throughput is 24.82 TFLOPS for the AI PRO 9600D versus 5.939 TFLOPS for the 890M, with both maintaining a 1:1 FP16 ratio at the same figures.

Memory configuration is a fundamental differentiator. The 890M relies entirely on system shared memory, with size, type, bus width, and bandwidth all listed as system dependent. The AI PRO 9600D carries 32 GB of GDDR6 memory on a 256-bit bus, delivering 576.0 GB/s of bandwidth. This dedicated memory arrangement gives the AI PRO 9600D a substantial advantage in memory-bound workloads.

The Verdict

The recorded data points to two entirely different performance classes. The 890M is an integrated graphics processor with a 15 W TDP, designed for mobile Strix Point systems, and its benchmark scores place it in the 45th percentile of all GPUs, just below the AMD Radeon Vega 8, GTX 960, GTX 465, and GTX 850M in average score. The AI PRO 9600D is a single-slot discrete workstation card with a 150 W TDP, 32 GB of GDDR6, and a 50th percentile placement, though it has no measured benchmark scores in the database.

The 890M's performance profile, as recorded, shows a capable integrated solution that trades closely with several older discrete GPUs. The AI PRO 9600D, by virtue of its specifications alone, offers roughly four times the FP32 throughput, three times the shading units, and a memory bandwidth of 576.0 GB/s versus the 890M's system-dependent shared memory. The data indicates the AI PRO 9600D is built for substantially heavier workloads, particularly those requiring large local memory capacity and high sustained throughput.

The 890M's higher boost clock of 2900 MHz compared to the AI PRO 9600D's 2020 MHz suggests the integrated part can spike to high frequencies briefly, but the AI PRO 9600D's higher base clock of 1080 MHz versus 400 MHz indicates a more sustained operating point. The AI PRO 9600D also supports PCIe 5.0 x16 versus the 890M's PCIe 4.0 x8, which affects data transfer ceilings.

From the data alone, the 890M is positioned for power-constrained mobile systems where integrated graphics are the only option, and its benchmark results confirm it performs in the vicinity of older discrete GPUs from the GTX 900 and 800 series. The AI PRO 9600D is positioned for professional or AI workloads requiring 32 GB of dedicated GDDR6 memory and a 256-bit memory bus, with a single-slot form factor and a 16-pin power connector.

Specification Differences

The two GPUs differ across nearly every specification field. The chip and architecture differ: Strix Point with RDNA 3.5 versus Navi 48 with RDNA 4.0. The generation differs: Navi III IGP (Strix Point Mobile) versus Radeon Pro Navi (Navi IV Series). The process node is identical at 4 nm from TSMC, but transistors differ at 34,000 million versus 53,900 million, and die size differs at 233 mm² versus 357 mm², with density at 145.9M per mm² versus 151.0M per mm².

Base clock is 400 MHz versus 1080 MHz, boost clock is 2900 MHz versus 2020 MHz, and the AI PRO 9600D adds a game clock of 1080 MHz while the 890M has none. Memory clock is system shared for the 890M versus 2250 MHz with 18 Gbps effective for the AI PRO 9600D. Memory size is system shared versus 32 GB, type is system shared versus GDDR6, bus width is system shared versus 256 bit, and bandwidth is system dependent versus 576.0 GB/s.

Shading units are 1024 versus 3072, TMUs are 64 versus 192, ROPs are 32 versus 96, and ray tracing cores are 16 versus 48. Pixel rate is 92.80 GPixel/s versus 193.9 GPixel/s, texture rate is 185.6 GTexel/s versus 387.8 GTexel/s, and FP32 is 5.939 TFLOPS versus 24.82 TFLOPS, with FP16 at the same figures for both.

TDP is 15 W versus 150 W. Slot width is IGP versus single-slot. Power connectors are none versus 1x 16-pin. The suggested PSU is listed as 450 W for the AI PRO 9600D and null for the 890M. Bus interface is PCIe 4.0 x8 versus PCIe 5.0 x16. Display outputs are portable device dependent for the 890M versus 1x DisplayPort 2.1a for the AI PRO 9600D. The AI PRO 9600D has physical dimensions of 241 mm length, 111 mm height, and 19 mm width, while the 890M lists none.

Both support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The release dates differ: 2024-07-14 for the 890M and 2025-12-10 for the AI PRO 9600D. The predecessors differ: Navi II IGP for the 890M and Radeon Pro Vega for the AI PRO 9600D. The production status is active for both, and neither has a listed successor or launch MSRP.

FAQ

Q: Which GPU has more shading units?

A: The AMD Radeon AI PRO 9600D has 3072 shading units, while the AMD Radeon 890M has 1024 shading units.

Q: What is the memory configuration of each GPU?

A: The AMD Radeon 890M uses system shared memory with system dependent bandwidth. The AMD Radeon AI PRO 9600D has 32 GB of GDDR6 memory on a 256-bit bus with 576.0 GB/s bandwidth.

Q: How do their FP32 performance figures compare?

A: The AMD Radeon AI PRO 9600D delivers 24.82 TFLOPS, while the AMD Radeon 890M delivers 5.939 TFLOPS.

Q: What are their TDP ratings?

A: The AMD Radeon 890M has a TDP of 15 W, and the AMD Radeon AI PRO 9600D has a TDP of 150 W.

Q: Which GPU has a higher boost clock?

A: The AMD Radeon 890M has a boost clock of 2900 MHz, which is higher than the AMD Radeon AI PRO 9600D's boost clock of 2020 MHz.

Q: What is the average benchmark score for each?

A: The AMD Radeon 890M has an average benchmark score of 9210 across its recorded tests. The AMD Radeon AI PRO 9600D has an average benchmark score of 0, as it has no recorded benchmark entries.

Q: What PCIe interface does each use?

A: The AMD Radeon 890M uses PCIe 4.0 x8, while the AMD Radeon AI PRO 9600D uses PCIe 5.0 x16.

Where Each One Wins

The AMD Radeon 890M wins in scenarios defined by power efficiency and integration. Its 15 W TDP, IGP slot width, and lack of power connectors make it suitable for mobile Strix Point systems where dedicated graphics are not an option. The recorded benchmark data shows its average score of 9210 places it just 0.1% behind the AMD Radeon Vega 8, 0.7% behind the GTX 960, 0.9% behind the GTX 465, and 1% behind the GTX 850M. This means the 890M delivers performance in the same band as those older discrete GPUs while consuming far less power and requiring no additional cooling or power connectors. Its higher boost clock of 2900 MHz also indicates the ability to spike to high frequencies when needed. For lightweight gaming, 2D workloads, and general mobile graphics, the 890M's recorded scores, including a PassMark G3D score of 8076 and a Geekbench Vulkan score of 40808, demonstrate a workable integrated solution.

The AMD Radeon AI PRO 9600D wins in scenarios requiring massive memory capacity, high sustained throughput, and professional connectivity. Its 32 GB of GDDR6 memory on a 256-bit bus with 576.0 GB/s bandwidth is a clear advantage over the 890M's system dependent shared memory. The FP32 throughput of 24.82 TFLOPS, pixel rate of 193.9 GPixel/s, and texture rate of 387.8 GTexel/s all point to compute-heavy or AI-oriented workloads where the 890M's 5.939 TFLOPS would be insufficient. The 150 W TDP and single-slot form factor with a 16-pin power connector indicate a dedicated workstation card meant for persistent load. The PCIe 5.0 x16 interface and DisplayPort 2.1a output further position it for modern professional workflows. The higher base clock of 1080 MHz versus 400 MHz for the 890M suggests the AI PRO 9600D maintains a consistent operating frequency rather than relying on boost spikes. The 50th percentile placement, though without measured benchmarks, reflects its specification-based standing above the 890M's 45th percentile.

The data shows a clear split: the 890M is the integrated solution for mobile power-constrained environments, while the AI PRO 9600D is the discrete workstation part for memory-intensive and high-throughput tasks. The lack of benchmark data for the AI PRO 9600D means its performance wins are inferred from specifications rather than measured results, while the 890M's wins are directly supported by its recorded scores.