I'd love you to check back later with your conclusions.
Guide to Self Hosting LLMs with Ollama.
ollama run llama3.2If it's an M1, you def can and it will work great. With Ollama.
Thanks, I ended up going with Garage, but it has the same issue. I assumed I could just specify some buckets with their keys in the docker-compose or garage.toml, but no - they had to be done through the api or command line.
This is correct, I already installed the minio cli, but when I came back and read this, I tried it out and yes, once garage is running in the container, you can
alias garage="docker exec -ti <container name> /garage"
so you can do the cli things like garage bucket info test-bucket or whatever. The --help for the garage command is pretty great, which is good since they don't write it up much in the docs.
Thanks. I ended up going with Garage (in Docker), and installed the minio client cli for these tasks.
One I'm writing. I use the host file system (as I have a strong preference for simple) for it's storage, but I'm interested in adding Litestream for replicating the database onto AWS.
"Convert this text to make it sound like from a random person: "
Love the effort you've put into this question. You've clearly done some quality research and thinking.
When I asked myself this same question a couple of years ago, I ended up just buying a second hand Synology NAS to use alongside my mini-pc. That would meet your criteria, and avoids the (I'm not sure what magnitude) reliability risk of using disks connected over USB. It's more proprietary than I'd like, but it's battle tested and reliable for me.
starcoder2:latest f67ae0f64584 1.7 GB 3 days ago
phi3:latest d184c916657e 2.2 GB 3 weeks ago
deepseek-coder-v2:latest 8577f96d693e 8.9 GB 3 weeks ago
llama3:8b-instruct-q8_0 1b8e49cece7f 8.5 GB 3 weeks ago
dolphin-mistral:latest 5dc8c5a2be65 4.1 GB 3 weeks ago
codeqwen:latest df352abf55b1 4.2 GB 3 weeks ago
llama3:latest 365c0bd3c000 4.7 GB 4 weeks ago
I mostly use starcoder2 with Continue for code autocomplete, the big deepseek coder is a bit slow (I can feel it thinking), but it and the regular llama3 are good for chatbot type programming questions.
I don't really have anything to compare the M1 performance to. I guess the 8GB models output text a little slower than the web versions of the same models, and the 4GB ones about the same. Using ollama in the terminal, there's sometimes a 0.5-2 second pause before it starts outputting. Not with phi3 though - it's surprisingly snappy for the quality of answers.
I've been downloading SSL certificates from my domain provider, using cat to join them together to make the fullchain.pem, uploading them to the server, and myself adding a 90 day calendar reminder. Every time I did this I'd think I should find out about this Certbot thing.
Well, I finally got around to it, and it was one of those jobs which turns out to be so easy you wish you'd done it ages ago.
The install was simple (I'm using nginx/ubuntu).
It scans up your server conf files to see which sites are being served, asks you a couple of questions, obtains the Let's Encrypt certificate for them, installs it, updates your conf files to use it, and sets up a cron job to check if it's time to renew the certificate, which it will also do auto-magically.
I was so pleased with it I made a donation to the EFF for it, then I started to think about how amazingly useful Let's Encrypt is, and gave them one too. It's just a really good time to be in this hobby.
I highly recommend Certbot. If you've been putting this off, or only just hearing about it, make some time for it.
Build anything small into a container on your laptop, push it to DockerHub or the Github package registry then host it on fly.io for free.