Running LLMs locally on MacOS

Phil (OmnisList) phil at
Wed Aug 30 09:30:20 UTC 2023


Have you played around with the Code Llama?

How in fact does it compare to just a simple Google search for getting 

I see "Continue" is within VScode, and can generate code for you...

Do you know what do the B figures mean? 7B, 13B, 34B and even 500B?

IT says that code Llama is a 7B that needs 16GB Memory...

Phil Potter
Based in Chester in the UK.

On 30/08/2023 06:55, Sten-Erik Björling wrote:
> Hi,
> Recommend that you look into - a solution to run Meta LLMs locally on your Mac. Several models supported - especially the coding support models and the uncensored ones are interesting.
> Demand a lot of memory for the larger ones, quite good performance - normal reservations apply…
> Take care all, all the best…
> Stene
> _______
> Sten-Erik Björling
> Enviro Data
> Kyrkogatan 5A 2 tr
> SE-972 32  Luleå
> Sweden
> E-Mail:s-e.bjorling at
> Mobile: +46-70-655 11 72
> Wire: @stenerikbjorling
> Skype: stenerikbjorling
> iChat:stene at
> Signal: +46 70 655 11 72
> FaceTime:stene at
> Telegram: @stenerikbjorling
> Hotmail / Messenger:stenerikbjorling at
> GMail:stenerikbjorling at
> ______
> This email and any files transmitted with it are confidential, may be legally privileged and are intended solely for the use of the individual or entity to whom they are addressed. If you are not the intended recipient, please note that any use, distribution, or reproduction of the contents of this email is strictly prohibited and may be unlawful. If you are not the intended recipient, please notify the sender by return email and destroy all copies of the original message, including any attachments. Thank you.
> Please note that we take reasonable precautions to prevent the transmission of viruses; however, we cannot guarantee that this email or its attachments are free from viruses. We only send and receive emails because we are not liable for any loss or damage resulting from the opening of this message and/or attachments.
> _____________________________________________________________
> Manage your list subscriptions at
> Start a new message ->mailto:omnisdev-en at  

More information about the omnisdev-en mailing list