OPEN MODELS / Vision language models
Run mistral-small3.1:24b on a cloud GPU
mistral-small3.1:24b is a Vision language models model by Ollama. 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: Building upon Mistral Small 3, Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and enhances long context capabilities up to 128k tokens without compromising text performance.
GPUs it fits on today
About 19 GB of GPU memory: the model download (4-bit by default) plus working memory.
| GPU | Memory | Per hour | 10 hours | |
|---|---|---|---|---|
| RTX 2080 Ti | 22 GB | $0.20 | $2.00 | Rent |
| Tesla P40 | 24 GB | $0.24 | $2.40 | Rent |
| RTX 4000Ada | 20 GB | $0.35 | $3.50 | Rent |
| RTX 3090 | 24 GB | $0.39 | $3.90 | Rent |
| Titan RTX | 24 GB | $0.40 | $4.00 | Rent |
Live starting prices from our catalog. You pay per second while the machine runs.
How to run mistral-small3.1:24b
- 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
Install Ollama and run the model
Run the commands below. Ollama downloads the model and serves an OpenAI-compatible API on port 11434.
curl -fsSL https://ollama.com/install.sh | sh
ollama run mistral-small3.1:24bWhy run it yourself?
Run document and image understanding on your own GPU: no per-image fee, and files stay on your machine.
Questions
- How much GPU memory does mistral-small3.1:24b need?
- By our estimate about 19 GB for inference (24B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run mistral-small3.1:24b?
- From $0.20 per hour on RTX 2080 Ti, billed per second. Ten hours cost about $2.00.
- 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