Igor Schlumberger

Hi @julianallchin What model do you want to push? Actually and du to copyright issues, models must be accredited by Ollama team. It would be nice to have a public...

It's a logical deduction that I made. If true, it's from the begining.

https://huggingface.co/julianallchin/mistral-sclip

Hi @azurwastaken it's a question of Memory. What is your Mac Memory? What is the size of the model you are using? If your Mac doesn't have enough memory, it...

I also have a MacBook Pro 32 go and when I run Mixtral, it's not so slow. Try to restart your mac and launch only Mixtral. If you have other...

Hi @songsh cluld you provide logs and if possible, à script to replicate the issue. If tou can verify if you are using the last version of Ollama, it would...

Hi @eliranwong JSON should not be slow. Did you try with other models? What OS do you use? Generally, when it's slow, that means that ollama doesn't have enough memory...

Version 0.1.29 fix an issue with json. Fixed issues where Ollama would hang when using JSON mode. Can you upgrade and tell if it works know?

Do you have a sample or a script I can run on a mac with large amount of memory to see if I can reproduce the slowness? I can only...

Hi @eliranwong I know you found a workarround, but it you try with latest version of Ollama, could you tell us is the issue is solve without workarround?