NVIDIA GeForce GTX 1650 Ti Max-Q vs NVIDIA RTX A3000 Laptop GPU vs NVIDIA GeForce GTX 1660 Super (Desktop)

The Nvidia GeForce GTX 1650 Ti Max-Q (N18P-G62) is a dedicated mid range graphics card for laptops based on the Turing architecture. The Max-Q variant is the power saving version of the mobile GTX 1650Ti with reduced clock speeds, performance and of course power consumption. It is using the same TU117 chip with 1,024 shaders. Therefore, it is intended for thin and light gaming laptops. Compared to the faster RTX 2000 GPUs (e.g. RTX 2060), the 1650 Ti integrates no Raytracing or Tensor cores.

There are two variants of the 1650Ti Max-Q, one with 35 Watt and 1035 - 1200 MHz and a faster 40 Watt version with a clock speed of 1200 - 1365 MHz. Both however are significantly lower clocked than the normal Max-P version with 50 / 55 Watt and 1350-1385 MHz. The memory is most likely clocked at 1250 MHz = 10,000 MHz effective (Gbps) in most laptops, although there might be versions with 1500 MHz = 12,000 Gbps.

The Turing generation did not only introduce raytracing for the RTX cards, but also optimized the architecture of the cores and caches. According to Nvidia the CUDA cores offer now a concurrent execution of floating point and integer operations for increased performance in compute-heavy workloads of modern games. Furthermore, the caches were reworked (new unified memory architecture with twice the cache compared to Pascal). This leads to 50% more instructions per clock and a 40% more power efficient usage compared to Pascal.

Compared to the bigger Turing chips (like the TU116 of the GTX 1660 Ti and the RTX lineup), the TU117 does not include the new NVENC encoder but an older one similar to the one used in Pascal and Volta.

The power consumption of the 1650 Ti Max-Q laptops is specified at 35 Watt TGP (Total Graphics Power) by Nvidia and therefore 25 Watt lower than the mobile GTX 1650 Ti in the same package (other variants can reach up to 80 Watt).

The NVIDIA RTX A3000 Laptop GPU or A3000 Mobile is a professional graphics card for mobile workstations. It is based on the GA104 Ampere chip and offers a similar performance to the consumer GeForce RTX 3060 Laptop GPU. However, it offers 256 more CUDA cores (4,096 versus 3,840) and is based on the bigger GA104 chip. The A3000 also supports PCIe 4.0 and integrates 32 RT-cores and 128 Tensor cores of the Ampere generation. It is available in different variants from 60 - 130 Watt (TGP) with different clock speeds (and performance). The GPU supports eDP 1.4b to connect the internal monitor and DisplayPort 1.4 and HDMI 2.1 for external connections.

In 2022 Nvidia released a slightly improved version of the RTX A3000 with more and faster graphics memory. The original 6 GB with 11 Gbits has been doubled to 12 GB GDDR6 clocked at 14 Gbits.

There is no more Max-Q variant (formerly used for the low power variants) but every OEM can choose to implement Max-Q technologies (Dynamic Boost, WhisperMode).

The raw performance should be similar to the GeForce RTX 3060 for laptops at the same TGP level. Both GPUs depend heavily on good cooling and a high TGP for good performance. At a similar power consumption level the RTX A3000 should be clearly faster than the old Quadro RTX 3000 and 3000 Max-Q. 

The GA104 chip offers 6,144 FP32 ALUs of which half can also execute INT32 instructions (i.e. 3,072 INT32 ALUs). With Turing all shaders could still execute FP32 or INT32 instructions. The raytracing and tensor cores on the chip were also improved according to Nvidia. The A3000 only uses 4,096 of the 6,144 CUDA cores. The Ampere chips also include an improved 5th generation video encoder (NVENC for H.264 and H.265) and a 7th generation decoder (for various formats now including AV1).

The GA104 chip is manufactured by Samsung in 8nm (8N), which is not quite able to keep up with the 7nm node at TSMC (e.g. used by AMD and also for the professional GA100 Ampere chip).