Jump to content
Main menu
Main menu
move to sidebar
hide
Navigation
Main page
Recent changes
Random page
freem
Search
Search
Appearance
Create account
Log in
Personal tools
Create account
Log in
Pages for logged out editors
learn more
Contributions
Talk
Editing
Openai/692bdd2b-98b4-8012-bcf8-fa145b46c56a
(section)
Add languages
Page
Discussion
English
Read
Edit
Edit source
View history
Tools
Tools
move to sidebar
hide
Actions
Read
Edit
Edit source
View history
General
What links here
Related changes
Special pages
Page information
Appearance
move to sidebar
hide
Warning:
You are not logged in. Your IP address will be publicly visible if you make any edits. If you
log in
or
create an account
, your edits will be attributed to your username, along with other benefits.
Anti-spam check. Do
not
fill this in!
=== π₯ 4. Real-World Behaviour for 16k Context === ===== MacBook Air M4 (24 GB) ===== * Loads the model. * First 8β10k tokens run fine. * Beyond 12kβ14k context β thermal + memory pressure β 10β20% slowdown. * Generation may drop from 18 t/s β 12β15 t/s under sustained load. ===== MacBook Air M4 (32 GB) ===== * Same peak speed * Much better stability * 16k context behaves cleanly with minimal slowdown * No meaningful thermal throttling at short bursts; long runs throttle ~5β10% ===== MacBook Pro M4 Pro ===== * Full 16k contexts are trivial * Stable 30β45 t/s even in long chats * No thermal drop * MLX can hold > 50 t/s stable on 20B-class ===== MacBook Pro M4 Max (36 GB) ===== * Highest throughput * Ideal for MLX * Zero throttling * Sustained 50β65 t/s for 20B
Summary:
Please note that all contributions to freem are considered to be released under the Creative Commons Attribution-ShareAlike 4.0 (see
Freem:Copyrights
for details). If you do not want your writing to be edited mercilessly and redistributed at will, then do not submit it here.
You are also promising us that you wrote this yourself, or copied it from a public domain or similar free resource.
Do not submit copyrighted work without permission!
Cancel
Editing help
(opens in new window)
