Willy Brauner: First time this WE, I installed an AI model o my local machine (devstrall-v2) and compiled it to gguf format with lama app. Consuming this model from the lama's chatbot interface works fine, but very slow when I send requests from Mistral Vibe. Has anyone already tested this CLI?

First time this WE, I installed an AI model o my local machine (devstrall-v2) and compiled it to gguf format with lama app. Consuming this model from the lama's chatbot interface works fine, but very slow when I send requests from Mistral Vibe. Has anyone already tested this CLI?