When you buy through links on our articles, Future and its syndicate partners may earn a commission.

Apple’s new M4 silicon significantly excels at rendering compared to other CPUs and GPUs, even discrete GPUs. Iniysa on X reports that Apple’s M4 Max performed audio transcoding with Whisper V3 Turbo in half the time of Nvidia’s Ampere-based RTX A5000 GPU, while using nearly eight times less power.

The M4 Max transcribed an audio file using the Whisper V3 Turbo in just 2:29 minutes with the MLX, drawing 25 watts of power. The RTX A5000 graphics card allegedly ran the same test in 4:33 while drawing 190 watts of power. That’s a 7.6x power consumption advantage in favor of the M4 Max.

It is worth mentioning that Nvidia RTX A5000 The GPU is part of the previous generation, so the newer Ada Lovelace-based GPUs will definitely perform better in this test. Regardless, the performance margin between the two is remarkable, especially considering the power consumption of both chips.

The RTX A5000 is a professional Ampere-based GPU with 8,192 CUDA cores, 24GB of GDDR6 memory, 768GB/s of memory bandwidth, and a total board power rating of 230W. The M4 Max, by contrast, is an APU with 12 performance cores and four efficiency cores paired with a robust media engine that supports all modern encoding and decoding standards, including AV1. The GPU has ten cores in total.

The main advantage of the M4 Max is the large number of encoders. Instead of having just one or two encoders like many GPUs today, the M4 Max features four total encoders, two regular video encoding engines and two Pro Res encoding and decoding engines.

Apple’s investment in heavy encoding performance no doubt helped fuel the M4 Max’s impressive transcoding victory over the RTX A5000. More impressively, the M4 Max’s benchmark run was done in the more balanced profile of the host cars. Adjusting the fans to run at full fan speed consistently reduces transcoding time by 10 seconds (down to 2:19).