Resources

What's the python code for utilizing this quantized model?

#35 opened 6 days ago by

enexorb

Create config.json

#34 opened 9 days ago by

Jash-RA

video

#33 opened 10 days ago by

goodasdgood

run

#32 opened 15 days ago by

goodasdgood

Is it using ggml to compute?

#30 opened about 1 month ago by

CHNtentes

FLUX GGUF conversion

#29 opened about 1 month ago by

bsingh1324

cant see the Q5_K_M gguf quant

#28 opened about 1 month ago by

Ai11Ali

Q6_K does not play as well with LoRAs

#25 opened about 1 month ago by

SubtleOne

Q8 vs Q4_1 vs FP8 on a 1070ti

#23 opened about 1 month ago by

gfl1973

Changelog

#22 opened about 2 months ago by

Shehab007

Which one is the best?

#21 opened about 2 months ago by

akiokawahito

Can you add Q4K_m please ?

#19 opened about 2 months ago by

mirek190

code for use this quantized model

#18 opened about 2 months ago by

Mahdimohseni0333

Compared to the regular FP8 model, what is the better performance of the 8BIT model here

#16 opened about 2 months ago by

demo001s

all K quants comparison using fp16/fp8 t5

#15 opened about 2 months ago by

Nelathan

What is the _K on the new files ?

#14 opened about 2 months ago by

Fabienne

Can it use LoRAs?

#13 opened about 2 months ago by

zdeto

Can you add a link to that "install instructions GitHub" ??? And possible a super simple ComfyUI demo workflow?

#12 opened about 2 months ago by

AlexData257

Please explain the difference between the two models

#11 opened about 2 months ago by

martjay

Can this kind of merged model be converted to GGUF?

#10 opened about 2 months ago by

kakaxi

My experience

#9 opened about 2 months ago by

SaisExperiments

k-quants possible?

#2 opened about 2 months ago by

CHNtentes