Hugging Face's logo

Join the conversation

Join the community of Machine Learners and AI enthusiasts.

Sign Up
Back to feed
unmodeled-tyler 
posted an update 1 day ago
Post
239
Mistral Vibe is awesome!

I've been playing around with it a bit today, and have really been enjoying myself. I'm somewhat picky with CLI tools, so design is important to me. I think Mistral nailed it there. It's easy, clean, intuitive, and Mistral provides free API access to their devstral models to get started which is great.

Yesterday I built an interactive model selector for ollama in Aider. I decided to also configure one for Vibe because simple, clean integrations make my brain happy.

I've included a screenshot below of Mistral Vibe running GLM-4.6 through Ollama Cloud and the model selector!
victor

wow thanks for your feedback makes me want to use it (I'm a Aider fan too so we're aligned) - how does glm-4.6 compares to using the mistral model in it?

·
unmodeled-tyler

Hey Victor! Great question, thanks for asking because there IS a difference (at least in how I set it up).

Mistral Vibe doesn't have a native ollama integration so I built that portion of it. My biggest goal was just to get it to work more than anything at first, and for the most part it does! The main issue I've seen so far is glm occasionally getting stuck in a loop, though it's almost certainly an interaction with my setup rather than the model itself. Vibe makes it super easy to just stop the model and get it back on track though, so that helps.

As for Mistral's model, I have been using Devstral 2 quite a bit (first time doing so!) and have really been enjoying it. The native devstral models don't have the looping issue, so that says to me it's most likely an issue with my integration (fixable!). Rarely there will be a tool call issue, but glm has consistently been able to resolve it without my intervention.

What I think is most interesting though, and a bit ironic, is that I wasn't able to get Mistral 3 Large to work via Ollama Cloud through Vibe. That's the same pipeline I ran glm through without an issue, so that bit is odd to me. It's in my backlog, but I've got a few other moving pieces at the moment.

In this post