Translation
Safetensors
mistral

When are official quantized versions?

#23
by Markobes - opened

Hi,
You wrote:

We recommend against using unofficial quantized versions for local deployment. We will soon release an official quantized model and develop a demo on Hugging Face Space.

But so far, the official quanta have not been released. What could be the reason for this? Do you plan to update the model and release a version with 20–30B that will be able to compete with general‑purpose models such as Gemma? It would be good to have a model of idiomatic translation that follows instructions, glossaries, and takes into account the cultural context.

Sign up or log in to comment