I’ve had pretty good luck running llamafile on my laptop. The speeds aren’t super fast, and I can only use the models that are Mistral 7B and smaller, but the results are good enough for casual use and general R and Python code.

Edit: my laptop doesn’t have a dedicated GPU, and I don’t think llamafile has support for Intel GPUs yet. CPU inference is still pretty quick.

My friends and I all use Simplex and have been very happy. There’s an annoying feature where messages in group chats are sometimes delivered out of order, but it’s easy enough to live with.

This reads like a poor attempt a guerrilla marketing.