Omer Celik
@omercelik.com
Engineer at Amazon &
Developer of tureng.com
Developer of tureng.com
Here is another test with Llama 4 Scout - 6 bit quantized version on M4 Max. Got ~30t/s which is faster than most of the hosted models.
April 6, 2025 at 10:03 PM
Here is another test with Llama 4 Scout - 6 bit quantized version on M4 Max. Got ~30t/s which is faster than most of the hosted models.
Tested Llama 4 Scout 4-bit quantized version on MLX and it is running at ~40t/s completely offline. It consumes around ~61GB of memory. It seems 64GB Macs won't be enough to run this without spilling into swap.
April 6, 2025 at 10:02 PM
Tested Llama 4 Scout 4-bit quantized version on MLX and it is running at ~40t/s completely offline. It consumes around ~61GB of memory. It seems 64GB Macs won't be enough to run this without spilling into swap.
Had a boat tour today. Great weather, great views.
May 7, 2023 at 11:21 PM
Had a boat tour today. Great weather, great views.
What a nice place to vote today! 😊
April 29, 2023 at 7:10 PM
What a nice place to vote today! 😊
Having a boat trip for the closing party (funeral?) of the Book Depository.
April 26, 2023 at 6:02 PM
Having a boat trip for the closing party (funeral?) of the Book Depository.
Goodbye Book Depository! You will be missed
April 26, 2023 at 12:52 PM
Goodbye Book Depository! You will be missed