Model reference · open weights

aya-23

LLMs CohereLabs Text gen 1 build Non-commercial 9k dl/mo

aya-23 is an open-weight language model from Cohere. aya-23-8B (FP16) weighs 16.1 GB; the smallest configuration that runs it is RTX 4090 24 GB.

Request Rent a GPU

For self-hosting, compare this build's requirements below with the GPU you plan to rent.

Aya 23 is an 8-billion parameter instruction fine-tuned language model developed by Cohere for multilingual text generation.
It supports 23 languages including English, French, German, Spanish, Italian, Portuguese, Japanese, and Korean, with a context length of 8192 tokens.
The model is released under the CC-BY-NC-4.0 license.

Summary of the CohereLabs/aya-23-8B model card, 2026-10-01

What it is

What it runs on

Memory and cards for aya-23-8B (FP16)

16.1 GBweights, file size

762 MBruntime overhead, at least

How much memory each request adds isn't estimated yet for this architecture. The weights need at least the cards below, plus room for the context.

How it works

Details

Languages

enfrdeesitptjakozharelfaplid