The Nvidia GeForce MX450 (N18S-G5, N18S-G5-B, N18S-LP codename) is a dedicated entry-level mobile graphics card for laptops. It uses the same TU117 chip as the GeForce GTX 1650 but with a reduced memory bus of 64 Bit. Furthermore, the MX450 is the first mobile GPU with PCIe Gen 4 x4 support.
Currently four different versions are available with different specifications and performance:
Especially the LP = Low Power variant is significantly slower than the typical 25 Watt variant.
The 25 Watt GDDR6 N18S-G5 should be up to 20% faster than a GeForce GTX 1050 but of course below a GTX 1650 (Max-Q). Therefore, demanding games like Horizon Zero Dawn should run lowest settings. Less demanding games like F1 2020 can be played in medium to high settings and full HD.
The TU117 chip is manufactured in 12nm at TSMC and thanks to the relatively low power consumption (TGP specified between 12 and 28.5 W) the dGPU is also suited for thin and light laptops. Mostly it is intended as an additional graphics card for Tiger Lake-U based laptops.
The Nvidia GeForce MX350 is a dedicated entry-level mobile graphics card for laptops. It was released in February 2020 and is based on the same GP107 Pascal chip with 640 shaders as the Nvidia GeForce GTX 1050 for laptops. The memory bus is cut in half to 64 bit (GDDR5).
First benchmarks however show a bit slower performance as the GTX 1050 and on par with a GTX 960M. Nvidia states on the product page that the MX350 offers 2.5x of the performance of a Intel Iris Plus Graphics G7 in an i7-1065G7 (vs 2x for the MX330). Therefore, demanding games of 2019 like The Division 2, Metro Exodus or Rage 2 will only run in lowest detail settings acceptable. Less demanding games like Fifa 20 should run fine in high settings and even 1080p. However, this is always also depending on the used processor and main memory. See below for detailed gaming benchmarks.
The GP107-670-A1 chip is manufactured in a 14 nm FinFET process at Samsung and offers a number of new features, including support for DisplayPort 1.4 (ready), HDMI 2.0b, HDR, Simultaneous Multi-Projection (SMP) as well as improved H.265 video de- and encoding (PlayReady 3.0). A full list of improvements and the new Pascal desktop GPUs is available in our dedicated Pascal architecture article.
In new Nvidia drivers drivers the GeForce MX350 appeared with the hardware ID 1C94.
The power consumption in our tests was lower than the average GTX 1050 (even Max-Q) and similar to the older MX graphics cards (as the TGP of 25 Watt suggests). Therefore, the GPU is suited for thin and light laptops.
The Intel Iris Xe MAX (DG1 Low Power - LP or iDG1LPDEV) is a dedicated PCIe 4.0 mobile entry-level graphics card with 96 execution units (EUs) based on the Gen 12 architecture. Compared to the integrated Intel Iris Xe in the Tiger Lake CPUs, the Xe MAX offers 4 GB dedicated LPDDR4x graphics memory (68 GB/s versus 56 GB/s for the MX350) and higher clock speeds of 1.65 GHz (vs. 1.35 GHz). Both support DP4A DLBoost instructions to speed up AI tasks and two media engines (including AV1 decoding in hardware). Currently the GPU is only available for Tiger Lake based laptops and offers some possibilities to use the iGPU and dGPU together (using the Deep Link software framework). The GPU uses hybrid graphics to turn off the Xe MAX when not in used (display ports are routed through the iGPU, but the Xe MAX features four dedicated display ports in comparison the the Nvidia GeForce MX350).
Furthermore, Intel supports to shift TDP between the two chips for better CPU performance or balancing graphics workloads.
The gaming performance is on average slightly better than a fast Intel Iris Xe iGPU with plenty of TDP and cooling headroom. There are even some games where the iGPU is faster thanks to Deep Link and sharing power and cooling. Intel targets 1080p gaming with low to medium settings with the GPU and provided examples where the MAX is on par or better than a dedicated Nvidia GeForce MX350.
According to Intel, the GPU is mostly aimed at content creators that can make use of the additional compute units, AI (DP4a) acceleration or media encoders.
As the Iris Xe Graphics, the Xe MAX supports Variable Rate Shading, Adaptive Sync, Async Compute, DirectX 12.1, OpenGL 4.6 and OpenCL 2.
As the Tiger Lake CPUs, the Iris Xe MAX dGPU is manufactured in the modern 10nm SuperFin process at Intel. Intel aims the Max-GPU for laptops with a combined power budget of 35 Watt and up. The power consumption of the GPU alone is specified similar to the 25W of the GeForce MX350 (we guess including the graphics memory).