OPEN MODELS / Language models (LLM)
Run BentoML on a cloud GPU
BentoML is a Language models (LLM) model by bentoml. See how much GPU memory it needs, which GPUs it fits on today and what it costs to run it yourself, billed per second.
From the project: The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!
GPUs it fits on today
Typical GPU memory for this kind of app: about 16 GB. Bigger models and higher resolutions need more.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| RTX A4000 | 16 GB | $0.19 | $1.90 | Rent |
| RTX 2080 Ti | 22 GB | $0.20 | $2.00 | Rent |
| RTX 5060 Ti | 16 GB | $0.20 | $2.00 | Rent |
| Tesla V100 | 16 GB | $0.22 | $2.20 | Rent |
| Q RTX 5000 | 16 GB | $0.24 | $2.40 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run BentoML
- 01
Rent a GPU
Pick one of the GPUs above. Billing is per second; stop the machine and you stop paying.
- 02
Open a terminal or Jupyter
Connect over SSH or open Jupyter in your browser. PyTorch and CUDA are ready to use.
- 03
Clone the app and follow its README
Run the commands below, then follow the project's README. Most apps start a web interface you can open through the machine's ports.
git clone https://github.com/bentoml/BentoML.git
cd BentoMLWhy run it yourself?
Your own LLM server has no per-token bill and no rate limit, and your data stays private. Pick a GPU by memory and serve the model with vLLM.
Questions
- How much GPU memory does BentoML need?
- By our estimate about 16 GB for inference (? parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run BentoML?
- From $0.19 per hour on RTX A4000, billed per second. Ten hours cost about $1.90.
- Do I need a subscription?
- No. You pay only for the time your machine runs, from your USD balance. Stop it whenever you are done.
Try it on your own GPU in minutes
Pick a GPU, open Jupyter or SSH and run any open model. You pay per second and can stop anytime; no subscription, no setup fee.
- Per-second billing in USD
- PyTorch and CUDA ready in minutes
- Rent from ChatGPT or Claude too