AMD Radeon AI PRO 9600D vs NVIDIA RTX 6000D Comparison

Head-to-Head Benchmarks

The recorded data shows a decisive performance gap between the AMD Radeon AI PRO 9600D and the NVIDIA RTX 6000D. The RTX 6000D carries an average benchmark score of 195,964 across its two recorded tests, placing it in the 98th percentile of all GPUs in the database. The Radeon AI PRO 9600D, by contrast, has no recorded benchmark scores and sits at the 50th percentile, with an average benchmark score of zero. That places the AMD card in the median position of the database distribution, while the NVIDIA card operates near the top.

The RTX 6000D delivers 97.04 TFLOPS of FP32 compute, compared to 24.82 TFLOPS on the Radeon AI PRO 9600D. That is a 3.9x advantage in raw single-precision throughput. The NVIDIA card also produces 1,516.3 GTexel/s of texture fill rate versus 387.8 GTexel/s on the AMD card, a 3.9x difference. Pixel throughput favors the RTX 6000D as well, at 466.6 GPixel/s versus 193.9 GPixel/s, a 2.4x margin.

Memory bandwidth tells a similar story. The RTX 6000D reaches 1.40 TB/s over a 448-bit GDDR7 interface, while the Radeon AI PRO 9600D delivers 576.0 GB/s over a 256-bit GDDR6 bus. The NVIDIA card has 84 GB of memory, the AMD card has 32 GB. In shading resources, the RTX 6000D fields 19,968 shading units, 624 texture mapping units, 192 ROPs, 156 RT cores, and 624 tensor cores. The Radeon AI PRO 9600D has 3,072 shading units, 192 TMUs, 96 ROPs, and 48 RT cores, with no tensor core count recorded.

The nearest rivals for the RTX 6000D in the database provide context for its standing. It scores 0.8% above the NVIDIA Tesla V100S PCIe 32 GB, 4.7% above the NVIDIA A100 SXM4 40 GB, 6.1% above the NVIDIA RTX 5000 Ada Generation, and 5.4% below the NVIDIA A100 PCIe 80 GB. These deltas place the RTX 6000D in a competitive band with some of the highest-performing accelerators in the database. The Radeon AI PRO 9600D has no nearest rivals listed, and with no benchmark scores recorded, the database offers no direct performance comparisons for it.

Clock behavior differs substantially. The RTX 6000D runs at a 1992 MHz base clock and boosts to 2430 MHz. The Radeon AI PRO 9600D has a 1080 MHz base clock, a 1080 MHz game clock, and a 2020 MHz boost clock. Despite the lower frequency, the AMD card operates at a much lower 150 W TDP against the RTX 6000D's 600 W TDP. The power efficiency profile is therefore inverted relative to the performance profile: the AMD card delivers 24.82 TFLOPS at 150 W, while the NVIDIA card delivers 97.04 TFLOPS at 600 W. Per watt, the Radeon AI PRO 9600D produces 0.165 TFLOPS/W and the RTX 6000D produces 0.162 TFLOPS/W, a near parity in efficiency despite the massive absolute performance gap.

FAQ

Q: Which card has the higher average benchmark score?

A: The NVIDIA RTX 6000D has an average benchmark score of 195,964 across two tests, while the AMD Radeon AI PRO 9600D has an average benchmark score of 0 with no recorded tests.

Q: How much memory does each card provide?

A: The RTX 6000D has 84 GB of GDDR7 memory on a 448-bit bus, and the Radeon AI PRO 9600D has 32 GB of GDDR6 memory on a 256-bit bus.

Q: What is the percentile ranking difference between the two cards?

A: The RTX 6000D sits in the 98th percentile of all GPUs in the database, while the Radeon AI PRO 9600D sits in the 50th percentile.

Q: Does the AMD card have tensor cores?

A: The database records no tensor core count for the Radeon AI PRO 9600D. The RTX 6000D has 624 tensor cores.

Q: How do the RT core counts compare?

A: The RTX 6000D has 156 RT cores, while the Radeon AI PRO 9600D has 48 RT cores, a 3.25x difference.

Q: What are the power requirements for each card?

A: The Radeon AI PRO 9600D has a 150 W TDP and a suggested 450 W PSU, while the RTX 6000D has a 600 W TDP and a suggested 1000 W PSU. Both use a single 16-pin power connector.

The Verdict

The recorded data indicates that the NVIDIA RTX 6000D is the dominant performer in nearly every measurable category. Its FP32 throughput of 97.04 TFLOPS is 3.9x that of the Radeon AI PRO 9600D. Its 1.40 TB/s memory bandwidth is 2.4x higher. Its 84 GB memory capacity is 2.6x larger. Its 98th percentile standing versus the AMD card's 50th percentile position reflects a card that belongs in a different performance class entirely.

Buyers who need maximum compute throughput, high memory bandwidth, large memory capacity, and tensor core support should select the RTX 6000D. The data shows it outperforms several established accelerators in the database, including the Tesla V100S PCIe 32 GB by 0.8% and the RTX 5000 Ada Generation by 6.1%. It trails only the A100 PCIe 80 GB among its nearest rivals, by 5.4%.

Buyers who prioritize low power draw and compact physical dimensions should consider the Radeon AI PRO 9600D. It operates at 150 W versus 600 W, and it is a single-slot card measuring 241 mm in length, 111 mm in height, and 19 mm in width. The RTX 6000D is dual-slot and measures 304 mm by 137 mm by 40 mm. The AMD card also has a significantly lower suggested PSU rating at 450 W versus 1000 W.

The RTX 6000D has a recorded launch MSRP of 8,565 USD. The Radeon AI PRO 9600D has no launch MSRP recorded in the database. The RTX 6000D also has a longer market presence, with a release date of 2025-07-13, while the Radeon AI PRO 9600D was released on 2025-12-10.

Specification Differences

The two cards differ across nearly every specification field. The Radeon AI PRO 9600D uses a 4 nm process node, the RTX 6000D uses 5 nm. Transistor counts are 53,900 million on the AMD chip and 92,200 million on the NVIDIA chip. Die size is 357 mm² for the AMD card and 750 mm² for the NVIDIA card. Transistor density is 151.0M per mm² on the AMD side and 122.9M per mm² on the NVIDIA side.

Clock speeds differ: the AMD card has a 1080 MHz base clock, a 1080 MHz game clock, and a 2020 MHz boost clock. The NVIDIA card has a 1992 MHz base clock and a 2430 MHz boost clock, with no game clock recorded. Memory clocks are 2250 MHz (18 Gbps effective) on the AMD card and 1560 MHz (25 Gbps effective) on the NVIDIA card.

Memory configuration diverges completely. The AMD card uses 32 GB of GDDR6 on a 256-bit bus with 576.0 GB/s bandwidth. The NVIDIA card uses 84 GB of GDDR7 on a 448-bit bus with 1.40 TB/s bandwidth.

Compute resources differ by large margins. The AMD card has 3,072 shading units, 192 TMUs, 96 ROPs, and 48 RT cores. The NVIDIA card has 19,968 shading units, 624 TMUs, 192 ROPs, 156 RT cores, and 624 tensor cores. The AMD card has no tensor core count recorded.

Output rates follow the resource counts. Pixel rate is 193.9 GPixel/s on the AMD card and 466.6 GPixel/s on the NVIDIA card. Texture rate is 387.8 GTexel/s on the AMD card and 1,516.3 GTexel/s on the NVIDIA card. FP32 and FP16 are both rated at 24.82 TFLOPS on the AMD card and 97.04 TFLOPS on the NVIDIA card, with both cards operating at 1:1 FP16 to FP32 ratios.

Power and physical specifications also differ. The AMD card has a 150 W TDP, the NVIDIA card has a 600 W TDP. The AMD card is single-slot, the NVIDIA card is dual-slot. Both use a single 16-pin power connector. Suggested PSU is 450 W for the AMD card and 1000 W for the NVIDIA card. The AMD card measures 241 mm by 111 mm by 19 mm; the NVIDIA card measures 304 mm by 137 mm by 40 mm. The AMD card has one DisplayPort 2.1a output, the NVIDIA card has four DisplayPort 2.1b outputs. Both use PCIe 5.0 x16 and support DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4.

Architecture Differences

The Radeon AI PRO 9600D is built on the Navi 48 chip using the RDNA 4.0 architecture, part of the Radeon Pro Navi (Navi IV Series) generation. Its predecessor is the Radeon Pro Vega. The RTX 6000D is built on the GB202 chip using the Blackwell 2.0 architecture, part of the Blackwell PRO W (x000) generation. Its predecessor is Workstation Ada.

Process technology differs by one node: the AMD card uses a 4 nm process, the NVIDIA card uses 5 nm. Both are fabricated by TSMC. The AMD chip packs 53,900 million transistors into 357 mm², achieving 151.0M transistors per mm². The NVIDIA chip packs 92,200 million transistors into 750 mm², achieving 122.9M transistors per mm². The AMD chip has a higher transistor density despite having fewer total transistors and a smaller die.

The RTX 6000D includes tensor cores, with 624 of them recorded, which the Radeon AI PRO 9600D lacks in the database. This is the most significant architectural feature difference, as tensor cores enable dedicated matrix math operations. The RT core counts also differ, with the NVIDIA card carrying 156 RT cores against 48 on the AMD card.

The NVIDIA card uses GDDR7 memory, the AMD card uses GDDR6. Memory bus width is 448-bit on the NVIDIA card versus 256-bit on the AMD card. The NVIDIA card also has four display outputs versus one on the AMD card, and the display output version is DisplayPort 2.1b on NVIDIA versus 2.1a on AMD.

Both cards share the same API support set: DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. Both are listed as Active in production status. The NVIDIA card was released earlier, on 2025-07-13, and the AMD card followed on 2025-12-10. Neither card has a successor recorded in the database.