Does it deployed on T4!

#4
by mnwato - opened

Hi, How did CohereForAI/aya-expanse-32b infered on T4 with 16GB of VRAM!
Did you deployed a quantized version? If yes, which quant?

Cohere For AI org

hey we don't use T4 for aya expanse inference. We use our API. T4 is required for a TTS model inference.

shivalikasingh changed discussion status to closed

Sign up or log in to comment