https://youtu.be/7MC8WV-6Z_E?feature=shared
Tldr: rtx 4080 is about 2x faster than the M3 pro. M3 Max results are unknown.
There were some results on an arstechina forum where people claimed the M3 Max was as fast as a 4070 desktop but verify the numbers for yourself!
https://arstechnica.com/civis/threads/the-m3-max-pro-performance-comparison-thread.1496840/page-2
“Max GPU: 3:26, this doesn't seem right based on prior items in this thread does it? CPU was pegged at 1526%
Figured it out. Had to set GPU preferences to Metal, it was defaulted to none.
Classroom, 300 Samples
Max GPU: 19.84 seconds (Optimized Kernels)
Junkshop, 400 Samples @2560 x 1440 (is Junkyard something different?)
Max GPU: 50.59 seconds (Optimizing Kernels)
Max GPU: 48.64 seconds (Optimized Kernels)
Ollama:
65.96 tokens/s
60.51 tokens/s
59.97 tokens/s
62.41 tokens/s”
While I do like new tech and certainly Apple M line of cpu+gpu chips on a single SOC are powerful, it needs to be compared to the right technology. Comparing an SOC with a single heat pipe versus a desktop class GPU with 2000 grams of heat sink is just not a good comparison. They are built for different things.
The consumer class 4000 series rtx is not a workstation class GPU. It is designed for intensive grunt work for gamers. Latency is optimized for gaming. So high-frequency clock speeds. The higher the better latency.
Apple M3 is geared towards the professional content creator class of user. Who does not like to be bothered by heavy GPU and fan noise. It won’t have the best latency but it has good access to the tools to help get professional work done.
Until Apple develop their own “GPU”with high frequency and heavy cooling requirements, they will just be dumbing down games to candy crush style avg latency gaming.
I really get sick of hearing that phrase.