Skip to content

Navigation Menu

Sign in
Sign up

Idea: MFlux should _default_ to downloading _suitable_ pre-quantized MFlux models... instead of unquantized HF Models #670

ianscrivener started this conversation in Ideas & Suggestions: Features
Discussion options

Say a new user runs mflux-generate-z-image-turbo -p 'a puffin on a cliff top' on a 16GB Mac that has no modelos downloaded..

Currently MFlux will try to download the full 32.9Gb Tongyi-MAI/Z-Image-Turbo models and _try_ to quantize it to a bf16 format models. This will likely crash.

Instead MFlux should (1) check the available memory and (2) download a suitably sized models... perhaps q3 text_encoder and a q5 transformer models.

You must be logged in to vote

Replies: 0 comments

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
discussion General discussion
1 participant

AltStyle によって変換されたページ (->オリジナル) /