AMD Radeon RX 7800M vs NVIDIA P106-100 Comparison

FAQ

Q: Which GPU has the higher average benchmark score?

A: The AMD Radeon RX 7800M records an average benchmark score of 27,883, while the NVIDIA P106-100 sits at 23,249. That places the RX 7800M in the 73rd percentile of all GPUs, versus the P106-100's 68th percentile.

Q: How do the two compare in DirectX 12 performance?

A: In the 3DMark Steel Nomad DX12 test, the RX 7800M scores 2,994 against the P106-100's 899, a 233% advantage. The RX 7800M also supports DirectX 12 Ultimate (12_2), while the P106-100 is limited to DirectX 12 (12_1).

Q: What is the memory configuration difference?

A: The RX 7800M has 12 GB of GDDR6 on a 192-bit bus with 432.0 GB/s bandwidth. The P106-100 has 6 GB of GDDR5 on the same 192-bit bus width, but only 192.2 GB/s bandwidth. That is more than double the memory capacity and over twice the bandwidth.

Q: Which GPU has the higher shading unit count?

A: The RX 7800M has 3,840 shading units, while the P106-100 has 1,280. This three-to-one ratio in shading units is a major contributor to the RX 7800M's FP32 compute output of 35.87 TFLOPS versus 4.375 TFLOPS.

Q: Are both GPUs still in production?

A: No. The RX 7800M is listed as Active production, released September 2024. The P106-100 is End-of-life, released June 2017.

Q: What is the power draw difference?

A: The RX 7800M has a 180 W TDP and uses no power connectors, as it is an integrated graphics processor (IGP) for portable devices. The P106-100 has a 120 W TDP, requires a 1x 6-pin power connector, and has a suggested PSU of 300 W.

Architecture Differences

The two GPUs come from entirely different architectural eras. The AMD Radeon RX 7800M uses the RDNA 3.0 architecture on the Navi 32 chip, built on a 5 nm TSMC process. The NVIDIA P106-100 uses the Pascal architecture on the GP106 chip, fabricated on a 16 nm TSMC process. That process gap explains much of the efficiency and density difference: the RX 7800M packs 28,100 million transistors into a 346 mm² die, yielding 81.2M transistors per mm². The P106-100 has only 4,400 million transistors on a 200 mm² die, for 22.0M per mm².

The RX 7800M belongs to the Navi Mobile (RX 7000M) generation with the codename Wheat Nas. The P106-100 comes from the Mining GPUs generation. This is a fundamental distinction: the P106-100 was designed for cryptocurrency mining, not graphics output, and accordingly has "No outputs" for display connectivity. The RX 7800M, by contrast, has display outputs described as "Portable Device Dependent," meaning it drives a laptop or handheld screen directly.

Compute capability differs sharply. The RX 7800M has 3,840 shading units, 240 texture mapping units, 96 ROPs, and 60 ray tracing cores. The P106-100 has 1,280 shading units, 80 TMUs, 48 ROPs, and no ray tracing cores. The RX 7800M also supports FP16 at a 1:1 ratio, delivering 35.87 TFLOPS for both FP32 and FP16. The P106-100 runs FP16 at a 1:64 ratio, producing only 68.36 GFLOPS. In practice, this means the RX 7800M can accelerate mixed-precision workloads far more effectively.

Memory architecture also diverges. The RX 7800M uses 12 GB GDDR6 at 2250 MHz with 18 Gbps effective, achieving 432.0 GB/s. The P106-100 uses 6 GB GDDR5 at 2002 MHz with 8 Gbps effective, reaching 192.2 GB/s. Both use a 192-bit bus, but the newer memory type and higher clocks give the RX 7800M a decisive bandwidth advantage.

The API feature sets reflect their respective generations. The RX 7800M supports DirectX 12 Ultimate (12_2), OpenGL 4.6, and Vulkan 1.4. The P106-100 supports DirectX 12 (12_1), OpenGL 4.6, and Vulkan 1.4. The RX 7800M's 12_2 feature level enables hardware ray tracing and mesh shaders, which the P106-100 cannot accelerate.

The Verdict

The data is unambiguous. The RX 7800M wins all three head-to-head benchmark comparisons, with margins ranging from 233% to 285%. For anyone building a portable gaming or workstation device, the RX 7800M is the clear choice. Its 12 GB frame buffer, 432.0 GB/s bandwidth, and 35.87 TFLOPS FP32 compute make it suitable for modern games and content creation workloads. The P106-100, with 6 GB GDDR5 and 4.375 TFLOPS, is a mining-specific relic that cannot even output video. It has no ray tracing support and its DirectX 12_1 feature level is a generation behind.

However, context matters. The P106-100 is End-of-life and was never intended for consumer graphics use. Its 120 W TDP and single 6-pin connector made it cheap to run in mining rigs, but with no display outputs, it is useless for a standard desktop build. The RX 7800M is Active, released in September 2024, and designed for the Navi Mobile generation. If you have a portable device that supports it, the RX 7800M is the only sensible pick. The P106-100 should only be considered if you specifically need a compute-only accelerator for a mining or server application, and even then its 68th percentile ranking versus the RX 7800M's 73rd percentile shows it is the weaker compute part.

Specification Differences

The two GPUs differ in nearly every measurable specification. The process node is 5 nm for the RX 7800M versus 16 nm for the P106-100. Transistor count is 28,100 million versus 4,400 million. Die size is 346 mm² versus 200 mm². Transistor density is 81.2M per mm² versus 22.0M per mm².

Clock speeds: base 1295 MHz versus 1506 MHz, boost 2335 MHz versus 1709 MHz. The RX 7800M also lists a game clock of 2145 MHz; the P106-100 has no game clock. Memory clock is 2250 MHz (18 Gbps effective) versus 2002 MHz (8 Gbps effective).

Memory: 12 GB GDDR6 versus 6 GB GDDR5. Both have a 192-bit bus, but bandwidth is 432.0 GB/s versus 192.2 GB/s. Shading units are 3,840 versus 1,280. TMUs are 240 versus 80. ROPs are 96 versus 48. The RX 7800M has 60 ray tracing cores; the P106-100 has none.

Pixel rate is 224.2 GPixel/s versus 82.03 GPixel/s. Texture rate is 560.4 GTexel/s versus 136.7 GTexel/s. FP32 is 35.87 TFLOPS versus 4.375 TFLOPS. FP16 is 35.87 TFLOPS (1:1) versus 68.36 GFLOPS (1:64).

TDP is 180 W versus 120 W. Slot width is IGP versus Dual-slot. Power connectors are None versus 1x 6-pin. The P106-100 has a suggested PSU of 300 W; the RX 7800M has none listed. Bus interface is PCIe 4.0 x16 versus PCIe 1.0 x16. Display outputs are Portable Device Dependent versus No outputs. Length is 250 mm (9.8 inches) for the P106-100; the RX 7800M has no listed dimensions.

DirectX support is 12 Ultimate (12_2) versus 12 (12_1). Release dates are September 2024 versus June 2017. Production status is Active versus End-of-life.

Head-to-Head Benchmarks

The three shared benchmark results tell a consistent story of dominance. In the 3DMark Steel Nomad DX12 test, the RX 7800M scores 2,994 against the P106-100's 899. That is a 233% delta, meaning the RX 7800M delivers more than triple the performance in this modern DirectX 12 workload. This test is particularly relevant for gaming, as it stresses the GPU's ability to handle current-generation rendering techniques.

In Geekbench OpenCL, the RX 7800M scores 120,778 versus 35,951, a 236% advantage. OpenCL is a general-purpose compute benchmark, and the RX 7800M's higher shading unit count and memory bandwidth translate directly into a massive lead. The 35.87 TFLOPS FP32 figure versus 4.375 TFLOPS predicts roughly an 8x compute advantage on paper, but the benchmark shows a more moderate 3.36x lead, indicating that memory bandwidth and driver efficiency also play a role.

In Geekbench Vulkan, the RX 7800M scores 126,668 versus 32,897, a 285% delta. This is the largest margin of the three tests. Vulkan is a low-level graphics API that scales well with raw hardware resources, and the RX 7800M's 60 ray tracing cores, 240 TMUs, and 96 ROPs allow it to pull further ahead. The P106-100's Pascal architecture, designed for mining rather than graphics, has no ray tracing hardware and only 48 ROPs, which limits its Vulkan throughput.

The RX 7800M also has additional benchmark data that the P106-100 lacks. Its Passmark G3D score is 17,613, its GPU compute score is 9,342, and it records 892 in Passmark G2D. The P106-100 has no corresponding Passmark entries in the database, so direct comparison is not possible for those tests. However, the average benchmark scores of 27,883 versus 23,249 show that the RX 7800M's overall performance envelope is roughly 20% higher when all available tests are averaged.

Where Each One Wins

The RX 7800M wins in every measured category. For gaming, its 233% lead in 3DMark Steel Nomad DX12 makes it the only viable option between the two. The 12 GB GDDR6 frame buffer handles modern game assets, and the 432.0 GB/s bandwidth prevents bottlenecks at high resolutions. The 60 ray tracing cores enable hardware-accelerated ray tracing, which the P106-100 cannot do at all.

For compute workloads, the RX 7800M's 236% OpenCL and 285% Vulkan leads show that it is the far stronger accelerator. Its 35.87 TFLOPS FP32 and 1:1 FP16 ratio make it suitable for AI inference, scientific computing, and rendering tasks. The P106-100's 68.36 GFLOPS FP16 is effectively negligible for modern mixed-precision workloads.

For portable devices, the RX 7800M's IGP form factor, no power connectors, and Portable Device Dependent display outputs make it drop-in compatible with laptops and handhelds. The P106-100 is a dual-slot card with a 6-pin connector, no display outputs, and a 300 W suggested PSU. It is physically incompatible with portable devices and functionally useless for any standard desktop display setup.

The P106-100's only theoretical advantage is its 120 W TDP, which is lower than the RX 7800M's 180 W. However, because the RX 7800M is an integrated GPU with no separate power connector, the system-level power draw is not directly comparable. The P106-100 requires a dedicated power supply and a PCIe slot, while the RX 7800M is soldered into a device. For a mining rig where power efficiency is paramount, the P106-100's lower TDP might be preferable, but its End-of-life status and 68th percentile ranking make it a poor long-term investment. The RX 7800M, at 73rd percentile, is the superior part by every benchmark metric in the database.