NVIDIA T600 vs NVIDIA T600 Laptop GPU vs NVIDIA Quadro T2000 Max-Q

The Nvidia T600 Desktop GPU is a professional graphics card for workstations that is based on the Turing architecture (TU117 chip). The desktop version only offers 640 of the 1024 cores and therefore also less than the T600 mobile (896 CUDA cores). The card offers 4 GB GDDR6 graphics memory connected with a 128 bit bus (up to 160 GB/s bandwidth). The T600 supports certified drivers (former Quadro line) for professional applications like CAD, 3D modelling, DCC, medicine, or visualization applications.

The maximum power consumption of the card is rated at 40W.

The Nvidia T600 Laptop GPU (or Quadro T600 for laptops) is a professional mobile graphics card that is based on the Turing architecture (TU117 chip). It is similar to the consumer GTX 1650 with 896 CUDA cores and a 128 Bit memory bus for GDDR6 graphics memory (10 Gbits). The chip is manufactured in 12nm FinFET at TSMC. The T600 was introduced as a refresh together with the T1200 and should be slightly slower than the older Quadro T1000 (2.6 versus 2.5 TFLOPS peak SP performance).

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 up to 50% more instructions per clock and a 40% more power efficient usage compared to Pascal. In contrary to the faster Quadro RTX cards, the T600 do not feature raytracing and Tensor cores.

Currently Nvidia only specifies the TDP of 25 Watt (the older T1000 had a TGP of 40-50 Watt). Therefore, the T600 should be well suited for thin and light laptops.

The Nvidia Quadro T2000 with Max-Q Design is a professional mobile graphics card that is based on the Turing architecture (TU117 chip). It is based on the consumer desktop GTX 1650 Ti therefore currently between a mobile GTX 1650 and GTX 1660 Ti. The chip is manufactured in 12nm FinFET at TSMC. Compared to the normal Quadro T2000, the Max-Q variants are clocked lower and work in a more efficient state. Currently, we know of two variants with different clock speeds and power consumptions (35 and 40 W).

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 up to 50% more instructions per clock and a 40% more power efficient usage compared to Pascal.

The performance in professional apps should be clearly lower than a normal (Max-P) Quadro T2000 due to the lower clock speeds, but still ahead the slower Quadro T1000 due to the higher shader count. Compared to consumer cards, the mobile GTX 1650 should be still slower.

Thanks to the relative low power consumption of the Quadro T2000 Max-Q, the GPU is suited for thin and light laptops. The used TU116 chip is manufactured in 12nm FFN at TSMC.