AMD Radeon RX 7600 vs NVIDIA P106-090 Comparison

FAQ

Q: How much faster is the AMD Radeon RX 7600 than the NVIDIA P106-090 in the recorded head-to-head benchmarks?

A: The RX 7600 wins all three recorded head-to-head tests. It leads by 353.8% in 3DMark Steel Nomad DX12, by 313.3% in Geekbench OpenCL, and by 85% in Geekbench Vulkan.

Q: What is the average benchmark score for each card, and where do they rank?

A: The RX 7600 has an average benchmark score of 15171 and sits in the 57th percentile of all GPUs. The P106-090 has an average score of 13470 and sits in the 54th percentile.

Q: Which card has more memory, and does the bus width differ?

A: The RX 7600 has 8 GB of GDDR6 memory on a 128 bit bus, while the P106-090 has 3 GB of GDDR5 memory on a 192 bit bus.

Q: Are there any display outputs on the P106-090?

A: No, the NVIDIA P106-090 has no display outputs. The AMD Radeon RX 7600 offers 1x HDMI 2.1a and 3x DisplayPort 2.1.

Q: What is the production status of each card?

A: The RX 7600 is listed as Active, while the P106-090 is End-of-life.

Q: Which card has a higher boost clock?

A: The RX 7600 boosts to 2655 MHz, compared to 1531 MHz for the P106-090.

Architecture Differences

The AMD Radeon RX 7600 is built on the RDNA 3.0 architecture using the Navi 33 chip, which goes by the codename Hotpink Bonefish. It belongs to the Navi III (RX 7000) generation and is fabricated on a 6 nm process at TSMC. The die measures 204 mm² and packs 13,300 million transistors, yielding a transistor density of 65.2M per mm². The NVIDIA P106-090, by contrast, uses the older Pascal architecture with the GP106 chip and is produced on a 16 nm process, also at TSMC. Its die is 200 mm², close in size, but it holds only 4,400 million transistors, giving a density of 22.0M per mm². This is a dramatic difference in transistor packing: the RX 7600 fits roughly three times more transistors into nearly the same silicon area.

The feature sets diverge sharply. The RX 7600 includes 32 ray tracing cores, which the P106-090 lacks entirely, and it supports DirectX 12 Ultimate (12_2) versus DirectX 12 (12_1) on the P106-090. The RX 7600 also supports FP16 at a 1:1 ratio with FP32, while the P106-090 runs FP16 at a 1:64 ratio, a major divergence in compute capability. Both cards support OpenGL 4.6 and Vulkan 1.4, but the underlying hardware generations are far apart. The RX 7600 is a modern gaming-focused GPU with display outputs and ray tracing support, while the P106-090 is a mining-oriented card with no display outputs at all. The bus interface also differs: the RX 7600 uses PCIe 4.0 x8, whereas the P106-090 uses PCIe 1.0 x1, a severe bandwidth constraint for the older card.

Clock speeds reinforce the architectural gap. The RX 7600 has a base clock of 1720 MHz, a game clock of 2250 MHz, and a boost clock of 2655 MHz. The P106-090 runs at a 1354 MHz base and 1531 MHz boost. Memory technology and bandwidth also separate them: the RX 7600 uses 8 GB GDDR6 at 18 Gbps effective with 288.0 GB/s bandwidth, while the P106-090 uses 3 GB GDDR5 at 8 Gbps effective with 192.2 GB/s bandwidth. The RX 7600 has a larger bus width advantage in effective throughput despite its narrower 128 bit interface, because the GDDR6 speed compensates. The P106-090's 192 bit bus cannot overcome its slower memory clock.

The Verdict

The data points to a decisive overall win for the AMD Radeon RX 7600. In every recorded head-to-head benchmark, it outperforms the NVIDIA P106-090 by a wide margin. The 3DMark Steel Nomad DX12 result shows a 353.8% lead, and Geekbench OpenCL shows a 313.3% lead. Even the smallest gap, Geekbench Vulkan at 85%, is substantial. The average benchmark scores reflect this: 15171 for the RX 7600 versus 13470 for the P106-090.

For gaming or any workload requiring display output, the P106-090 is effectively disqualified by its lack of outputs, while the RX 7600 provides modern connectivity. The RX 7600 also supports ray tracing hardware, which the P106-090 does not. The P106-090 is end-of-life, whereas the RX 7600 remains active. The only area where the P106-090 shows any advantage is power draw: its 75 W TDP is less than half of the RX 7600's 165 W, and its suggested PSU is 250 W versus 450 W. But that efficiency advantage does not translate into competitive performance. The RX 7600 is the clear choice for anyone needing actual graphics capability, and the P106-090 should only be considered in niche compute or mining scenarios where its low power and lack of outputs are acceptable.

Specification Differences

The two cards differ in nearly every measurable specification. The RX 7600 has 2048 shading units, 128 TMUs, and 64 ROPs, while the P106-090 has 768 shading units, 48 TMUs, and 48 ROPs. The RX 7600 adds 32 ray tracing cores; the P106-090 has none. Pixel rate is 169.9 GPixel/s for the RX 7600 versus 73.49 GPixel/s for the P106-090. Texture rate is 339.8 GTexel/s versus 73.49 GTexel/s. FP32 compute is 21.75 TFLOPS versus 2.352 TFLOPS. FP16 is 21.75 TFLOPS (1:1) versus 36.74 GFLOPS (1:64).

Memory configuration differs as well. The RX 7600 uses 8 GB GDDR6 on a 128 bit bus with 288.0 GB/s bandwidth. The P106-090 uses 3 GB GDDR5 on a 192 bit bus with 192.2 GB/s bandwidth. Memory clocks are 2250 MHz (18 Gbps effective) versus 2002 MHz (8 Gbps effective). Power requirements: the RX 7600 has a 165 W TDP with a 1x 8-pin connector and a 450 W suggested PSU. The P106-090 has a 75 W TDP with a 1x 6-pin connector and a 250 W suggested PSU. Both are dual-slot cards, but the P106-090 is longer at 250 mm (9.8 inches) versus 204 mm (8 inches) for the RX 7600. The RX 7600 has a height of 115 mm (4.5 inches); the P106-090's height is not recorded.

The RX 7600 supports DirectX 12 Ultimate (12_2), while the P106-090 supports DirectX 12 (12_1). Both support OpenGL 4.6 and Vulkan 1.4. The bus interface is PCIe 4.0 x8 for the RX 7600 and PCIe 1.0 x1 for the P106-090. Display outputs: the RX 7600 has 1x HDMI 2.1a and 3x DisplayPort 2.1; the P106-090 has none. Release dates are far apart: the RX 7600 launched on 2023-05-24, while the P106-090 launched on 2017-07-30. The RX 7600 has a launch MSRP of 269 USD; the P106-090 has no recorded MSRP. The RX 7600's predecessor is Navi II and successor is Navi IV; the P106-090 has no recorded predecessor or successor.

Head-to-Head Benchmarks

The recorded head-to-head data contains three tests, and the RX 7600 wins all of them. The largest margin is in 3DMark Steel Nomad DX12, where the RX 7600 scores 2310 against 509 for the P106-090, a delta of 353.8%. This test is a modern DX12 workload, and the RX 7600's newer architecture and ray tracing support likely contribute to the overwhelming gap. The P106-090's score of 509 is less than a quarter of the RX 7600's result.

In Geekbench OpenCL, the RX 7600 scores 88051, while the P106-090 scores 21304, a delta of 313.3%. This compute-oriented test highlights the massive FP32 and FP16 advantage of the RX 7600. The RX 7600's 21.75 TFLOPS FP32 and 21.75 TFLOPS FP16 (1:1) dwarf the P106-090's 2.352 TFLOPS FP32 and 36.74 GFLOPS FP16 (1:64). The P106-090's FP16 throughput is effectively negligible by comparison, which explains the large OpenCL deficit.

The closest result is Geekbench Vulkan, where the RX 7600 scores 34401 versus 18596 for the P106-090, a delta of 85%. Even here, the RX 7600 nearly doubles the P106-090's score. Vulkan is a lower-level API that can sometimes narrow gaps between architectures, but the raw compute and memory bandwidth differences remain too large for the P106-090 to close the divide. The RX 7600's 288.0 GB/s memory bandwidth, versus 192.2 GB/s for the P106-090, and its much higher shading unit count, keep it firmly ahead.

Where Each One Wins

The AMD Radeon RX 7600 wins in every performance dimension recorded. It dominates in modern DX12 workloads, as shown by the 3DMark Steel Nomad result with a 353.8% lead. It dominates in compute-heavy OpenCL tasks, as shown by the 313.3% lead in Geekbench OpenCL. It also wins in Vulkan, with an 85% lead in Geekbench Vulkan. For gaming, the RX 7600's ray tracing cores, DirectX 12 Ultimate support, and display outputs make it the only viable choice for actual gameplay. Its 8 GB GDDR6 memory is more than double the P106-090's 3 GB GDDR5, which matters for modern game textures and resolutions.

The NVIDIA P106-090 wins only in power efficiency. Its 75 W TDP is less than half of the RX 7600's 165 W, and its suggested PSU of 250 W is well below the RX 7600's 450 W. It also uses a single 6-pin connector instead of an 8-pin. In a mining or compute context where display output is irrelevant and power draw is the primary constraint, the P106-090 could be preferable. Its 192 bit memory bus, while paired with slower GDDR5, still provides 192.2 GB/s of bandwidth, which is respectable for a 75 W card. However, its PCIe 1.0 x1 interface severely limits data transfer with the host system, which could bottleneck many workloads.

The production status also favors different use cases. The RX 7600 is Active, meaning it is still manufactured and supported. The P106-090 is End-of-life, so it is no longer produced. For a long-term system, the RX 7600 is the safer investment. For a low-power, minimal-footprint compute task that does not require display output and can tolerate a PCIe 1.0 x1 interface, the P106-090 has a niche. But the benchmark data is unambiguous: the RX 7600 outperforms the P106-090 by margins ranging from 85% to over 350% across all recorded tests, and its average benchmark score is 15171 versus 13470. The P106-090's only recorded advantages are power draw and physical length, and those do not compensate for the massive performance deficit.