AMD Radeon RX 6600M vs NVIDIA P106-100 Comparison

The AMD Radeon RX 6600M and the NVIDIA P106-100 are two very different graphics processors that nonetheless land in the same performance neighborhood according to aggregate benchmark data. The RX 6600M is a modern mobile gaming chip built on RDNA 2.0, while the P106-100 is a mining-oriented desktop card based on the older Pascal architecture. Their average benchmark scores are nearly identical—23,273 for the AMD part versus 23,249 for the NVIDIA part—a difference of just 0.1% in favor of the RX 6600M. Despite this statistical tie in overall averages, the head-to-head benchmark results tell a far more lopsided story, with the AMD card winning all three direct comparisons by substantial margins. The following analysis breaks down those results, the architectural reasons behind them, and what each card is best suited for based strictly on the available data.

Head-to-Head Benchmarks

The direct comparison data shows a decisive sweep for the AMD Radeon RX 6600M across all three shared benchmark tests. The largest gap appears in Geekbench Vulkan, where the RX 6600M scores 73,740 against the P106-100’s 32,897. That is a delta of 124.2%, meaning the AMD card delivers more than double the performance in this API. The margin is so wide that it suggests fundamental differences in how each architecture handles Vulkan workloads, not just a small clock speed advantage.

The Geekbench OpenCL test also favors the RX 6600M heavily, with a score of 67,765 versus 35,951 for the P106-100. The deltaPct here is 88.5%, approaching double the raw compute output. This result aligns with the FP32 throughput figures in the specification data: the RX 6600M is rated at 8.659 TFLOPS while the P106-100 manages 4.375 TFLOPS. The AMD card’s compute advantage is nearly exactly 2:1, which is reflected in the OpenCL score gap. The P106-100’s FP16 performance is even more restricted at 68.36 GFLOPS (1:64 ratio), though that figure does not directly appear in the head-to-head tests.

The smallest but still substantial win for the RX 6600M comes in 3DMark Steel Nomad DX12, where it scores 1,495 against 899 for the P106-100. The deltaPct of 66.3% shows a clear advantage in modern DirectX 12 gaming workloads. This is a particularly relevant result because it represents a contemporary graphics workload rather than a pure compute test. All three head-to-head tests result in wins for the RX 6600M, giving it a 3-0 record in direct comparisons. The NVIDIA card’s only consolation is that its average benchmark score across all tests—23,249—is virtually tied with the AMD card’s 23,273, a difference of only 0.1% that places both cards at the 68th percentile among all GPUs.

Architecture Differences

The two cards come from different manufacturing generations and process nodes. The RX 6600M uses the Navi 23 chip on TSMC’s 7 nm process, packing 11,060 million transistors into a 237 mm² die. That works out to a transistor density of 46.7 million per square millimeter. The P106-100, by contrast, uses the GP106 chip on TSMC’s 16 nm process, with 4,400 million transistors on a 200 mm² die and a density of 22.0 million per square millimeter. The newer process node gives the AMD card a density advantage of more than 2:1.

The memory subsystems differ significantly as well. The RX 6600M carries 8 GB of GDDR6 memory on a 128-bit bus, delivering 224.0 GB/s of bandwidth. The P106-100 has 6 GB of GDDR5 on a wider 192-bit bus, but its bandwidth is lower at 192.2 GB/s. The AMD card’s memory clock is 1750 MHz (14 Gbps effective) versus 2002 MHz (8 Gbps effective) for the NVIDIA card. The wider bus on the P106-100 cannot compensate for the slower memory technology.

Core counts also favor the AMD architecture. The RX 6600M has 1,792 shading units, 112 texture mapping units, and 64 raster operation units, plus 28 dedicated ray tracing cores. The P106-100 has 1,280 shading units, 80 TMUs, and 48 ROPs, with no ray tracing cores at all. The AMD card’s pixel rate is 154.6 GPixel/s versus 82.03 GPixel/s for the NVIDIA card, and its texture rate is 270.6 GTexel/s versus 136.7 GTexel/s. Both figures are roughly double for the RX 6600M.

API support also diverges. The RX 6600M supports DirectX 12 Ultimate (12_2), while the P106-100 is limited to DirectX 12 (12_1). Both cards support OpenGL 4.6 and Vulkan 1.4. The AMD card’s FP16 throughput is 17.32 TFLOPS with a 2:1 ratio, whereas the P106-100’s FP16 is just 68.36 GFLOPS with a 1:64 ratio—a massive difference in half-precision compute capability.

Where Each One Wins

Based on the benchmark data, the RX 6600M wins in every category where both cards were tested. Its 66.3% lead in 3DMark Steel Nomad DX12 indicates a strong advantage in modern gaming titles that use DirectX 12 features. The 124.2% lead in Geekbench Vulkan suggests the AMD card is particularly well-suited to Vulkan-based games and applications. The 88.5% lead in Geekbench OpenCL points to superior general-purpose compute performance, which benefits content creation, scientific workloads, and other GPU-accelerated tasks.

The P106-100 has no benchmark wins in the head-to-head data. Its only area of potential advantage comes from its specification sheet: it is a dual-slot card with a 250 mm length (9.8 inches) and a 1x 6-pin power connector, while the RX 6600M is an IGP (integrated graphics processor) with no power connectors and portable device dependent display outputs. That makes the P106-100 a more conventional desktop installation, but it also lacks any display outputs entirely—a consequence of its mining-oriented design. The P106-100 also has a higher TDP at 120 W versus 100 W for the RX 6600M, despite delivering far less compute performance.

The RX 6600M’s ray tracing cores are a feature the P106-100 simply does not have. While no ray tracing benchmark appears in the data, the presence of 28 dedicated RT cores indicates hardware-level support for that workload, which the Pascal-based NVIDIA card cannot match. The AMD card also supports a newer DirectX version (12_2 versus 12_1), which may matter for future game compatibility.

FAQ

Q: Which card has the higher average benchmark score?

A: The AMD Radeon RX 6600M has an average benchmark score of 23,273, which is 0.1% higher than the NVIDIA P106-100’s 23,249. Both cards sit at the 68th percentile among all GPUs.

Q: How much faster is the RX 6600M in Vulkan performance?

A: In Geekbench Vulkan, the RX 6600M scores 73,740 versus 32,897 for the P106-100, a delta of 124.2%.

Q: Does the P106-100 have any ray tracing capability?

A: No. The P106-100 has no ray tracing cores listed in its specifications, while the RX 6600M includes 28 dedicated ray tracing cores.

Q: What are the memory specifications for each card?

A: The RX 6600M has 8 GB of GDDR6 on a 128-bit bus with 224.0 GB/s bandwidth. The P106-100 has 6 GB of GDDR5 on a 192-bit bus with 192.2 GB/s bandwidth.

Q: Which card has a higher power consumption rating?

A: The P106-100 has a TDP of 120 W, while the RX 6600M is rated at 100 W.

Q: Are both cards still in production?

A: No. Both are listed as end-of-life products. The RX 6600M was released on 2021-05-30, and the P106-100 was released on 2017-06-18.

Specification Differences

The two cards differ in nearly every major specification category. The RX 6600M uses a 7 nm process from TSMC, while the P106-100 uses a 16 nm process. Transistor count is 11,060 million versus 4,400 million, and die size is 237 mm² versus 200 mm². Clock speeds differ with the RX 6600M at 2068 MHz base and 2416 MHz boost, compared to 1506 MHz base and 1709 MHz boost for the P106-100.

Memory capacity is 8 GB GDDR6 versus 6 GB GDDR5, with bus widths of 128 bit versus 192 bit. Bandwidth favors the AMD card at 224.0 GB/s versus 192.2 GB/s. Shading units are 1,792 versus 1,280, TMUs are 112 versus 80, and ROPs are 64 versus 48. The RX 6600M has 28 ray tracing cores; the P106-100 has none.

Pixel rate is 154.6 GPixel/s versus 82.03 GPixel/s, and texture rate is 270.6 GTexel/s versus 136.7 GTexel/s. FP32 performance is 8.659 TFLOPS versus 4.375 TFLOPS, and FP16 is 17.32 TFLOPS versus 68.36 GFLOPS. The TDP is 100 W versus 120 W. The RX 6600M is an IGP with no power connectors, while the P106-100 is dual-slot with a 250 mm length and a 1x 6-pin connector. The RX 6600M uses PCIe 4.0 x8, while the P106-100 uses PCIe 1.0 x16. Display outputs are portable device dependent on the AMD card and entirely absent on the NVIDIA card. The RX 6600M supports DirectX 12 Ultimate (12_2), while the P106-100 supports DirectX 12 (12_1).

The Verdict

The data points to a clear choice for most workloads: the AMD Radeon RX 6600M outperforms the NVIDIA P106-100 in every direct benchmark comparison. The RX 6600M is 66.3% faster in 3DMark Steel Nomad DX12, 88.5% faster in Geekbench OpenCL, and 124.2% faster in Geekbench Vulkan. It also offers more memory (8 GB versus 6 GB), higher bandwidth (224.0 GB/s versus 192.2 GB/s), and more than double the FP32 compute throughput (8.659 TFLOPS versus 4.375 TFLOPS). For gaming, the RX 6600M’s newer DirectX 12 Ultimate support and 28 ray tracing cores are significant advantages. For compute, its FP16 capability of 17.32 TFLOPS dwarfs the P106-100’s 68.36 GFLOPS.

The P106-100’s only technical advantages are its wider 192-bit memory bus and dual-slot desktop form factor with a 6-pin power connector. But these do not translate into any performance wins in the available data. The P106-100’s lack of display outputs makes it unsuitable for any traditional graphics use case, limiting it to mining or compute-only roles where its 120 W TDP and older architecture are still functional but outperformed.

Given the 3-0 head-to-head record and the substantial deltas in every test, the RX 6600M is the superior choice for any application that can use its features. The P106-100 might be selected for a specific desktop build where its dual-slot size and 6-pin connector are required, but the performance data offers no reason to prefer it. The RX 6600M wins on performance, efficiency (100 W versus 120 W), memory capacity, and modern feature support.