You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I guess the right way to test it is to run llama-bench compiled with different options. I am just not sure what the options are, and it takes forever on my 8G sushi laptop.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Did anybody tried benchmarking BLAS (OpenBLAS) vs BLIS?
I am trying to figure out what is the optimal backend for Homebrew compiled version (https://github.com/Homebrew/homebrew-core/blob/master/Formula/l/llama.cpp.rb).
I guess the right way to test it is to run
llama-bench
compiled with different options. I am just not sure what the options are, and it takes forever on my 8G sushi laptop.llama-bench -m ~/.cache/llama.cpp/unsloth_gemma-3-4b-it-GGUF_gemma-3-4b-it-Q4_K_M.gguf
Beta Was this translation helpful? Give feedback.
All reactions