Phi-4 14B (Ollama)

Microsoft's compact model trained on high-quality synthetic data — strong maths and reasoning for 14B.

Overview

Phi-4 punches above its size on reasoning benchmarks. The 4-bit Ollama build leaves most of the GPU free for large batches.

Key features

• ✓
  Small and fast
• ✓
  Good at maths
• ✓
  MIT licence

Use cases

• →
  Lightweight assistants
• →
  Classification at scale
• →
  Education apps

On this template

Runs on the Ollama template, exposing its Ollama API at a private HTTPS address. You also get root SSH and JupyterLab.

OLLAMA_PULL

phi4:14b

Quick start

1. Click Deploy and pick an available GPU — only offers with enough VRAM are shown.
2. Wait for the status to turn running. The first start downloads the model, which can take a few minutes.
3. Use the connection details on your rental page:

curl -u edge:<app-token> https://r12-abcd1234-app.gpu.clearlayer.ca/api/generate \
  -d '{"model": "phi4:14b", "prompt": "Hello!", "stream": false}'

import requests

r = requests.post("https://r12-abcd1234-app.gpu.clearlayer.ca/api/chat", auth=("edge", "<app-token>"), json={
    "model": "phi4:14b", "stream": False,
    "messages": [{"role": "user", "content": "Hello!"}],
})
print(r.json()["message"]["content"])