With the release of its new trillion-parameter model, Mistral is hoping to demonstrate it’s “still in the race” to build frontier-level artificial intelligence.
I’m really hoping Soofi models are going to be good. Because afaict they’ll be the first (and so far only) open source (not just open weight) models in the ~30B parameters range.
(if you’re about to send me a rude prompt about how this could have been a cron job, i completely agree with you but i already had the dang thing up and i wanted to see if it could do it)
Just because you used “prompt” instead of “post”, for a second I thought that this was the model’s response to you after you asked it for a solution to monitor 😂
I’m really hoping Soofi models are going to be good. Because afaict they’ll be the first (and so far only) open source (not just open weight) models in the ~30B parameters range.
You might be interested in these:
https://ifm.ai/blog/k2/
Thank you very much, I hadn’t heard about this model coming out anywhere!
Seems like I’ll need to wait just a bit more for it to be available in Ollama. As soon as it’s there I’ll try it out :)
No problem! The company who provides the models also forked llama.cpp while they wait for their PR to be approved if you’re curious about it.
https://github.com/ifm-ai/llama.cpp/tree/model/K2Horizon
Yeah, it seems the llama.cpp changes have been merged in the last 24 hours. I’m hoping ollama makes them available this week.
Oh this is news to me lmao. Brb, looks like I need to make some updates to my server 😂
Thanks for the heads up!
I’ve been using the 7b version for about 2 weeks now to monitor my basic k3s metrics and send me emails about it!
Fun Fact, it is difficult to convince this thing it isn’t Claude without a system prompt
(if you’re about to send me a rude prompt about how this could have been a cron job, i completely agree with you but i already had the dang thing up and i wanted to see if it could do it)
i have a web ui for it if anyone wants to try
Why not just use the model to write you a cron job :p
Just because you used “prompt” instead of “post”, for a second I thought that this was the model’s response to you after you asked it for a solution to monitor 😂
That’s awesome to hear, I’m glad it’s working well for you!
Thanks for sharing! Never heard of them but their smaller models (especially the 36B and 32B Model) sound very promising for lcoal deployments.
However it is kinda strange that the 32B model performs that much worse in Terminal-Bench 2.1 compared to the 36B parameter model.
There’s also https://apertus-ai.org/. Not sure what sizes they have
The good Apertus model is too large at 70B, unfortunately. The 8B model is much too small to be useful for what I need.