Will Apple market its NPU by token/s in its September iPhone 16 announcement?
7
52
Ṁ110Ṁ240
Oct 1
60%
chance
1D
1W
1M
ALL
When running a LLM model locally, token/s is a new metric. For example when running the open source Llama3 8B:
-a typical multi core Xeon server processor reach about 10T/s.
-RTX 2070 GPU reach 20T/s
-RTX 4070 GPU reach 40T/s
-8 Groq’s specialized LPU connected together reach 750T/s
I haven’t seen a mobile phone brand market its neural processor by token/s.
Get Ṁ600 play money
Related questions
What will be the price of the iPhone 16 at launch?
Apple opens public APIs for using the Apple Neural Engine in 2023 or 2024?
60% chance
What will be true about the new iPhone 16?
Do you think Apple's new AI features will be launched in September 2024, with the new iOS update or before?
Will Apple officially announce the iPhone Ultra in 2024?
20% chance
Will Apple generative AI apply to models less premium than iPhone 15 at launch?
41% chance
Will the Apple iPhone 16 (or at least one of iPhone 16’s models) have generative AI capabilities?
86% chance
Will Apple announce its own GPU in 2024?
15% chance
Will Apple recall the iPhone 15s?
12% chance
What will be the price of iPhone 16's cheapest model?