Hi, I need to deploy a few small models for demo’s. The demo’s will only be run for a few hours off and on over the course of a month or two. I don’t want to pay for huge amounts of hosting, but I absolutely need to have on-demand full usage of GPU and RAM so they behave correctly during the demos.…

On Demand GPU model hosting?

remg1997 February 20, 2024, 10:13pm 2

Serverless GPUs from inferless? Are your demos for running inference?

Topic		Replies	Views
Cheaper fine-tuning + hosting for Llama/Mistral — would this help anyone Beginners	1	30	August 22, 2025
What hardware do you use to train your models? Cloud or local? Intermediate	0	797	October 31, 2022
Serverless Spaces Spaces	2	384	January 18, 2024
How Huggingface pricing works for model Deployment? Inference Endpoints on the Hub	2	3414	October 20, 2023
Calculate costs for multiple models in same machine Inference Endpoints on the Hub	0	294	September 5, 2023