OPEN MODELS / Language models (LLM)
Run phi4-reasoning:14b on a cloud GPU
phi4-reasoning:14b is a Language models (LLM) 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: Phi 4 reasoning and reasoning plus are 14-billion parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
GPUs it fits on today
About 14 GB of GPU memory: the model download (4-bit by default) plus working memory.
| 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 phi4-reasoning:14b
- 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 phi4-reasoning:14bWhy 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 phi4-reasoning:14b need?
- By our estimate about 14 GB for inference (14B parameters). Higher resolution, longer context or bigger batches need more.
- How much does it cost to run phi4-reasoning:14b?
- 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