Bonus: Top up now and we'll double your first deposit — get x2 credits instantly.

Phi-4: Self-Hosting & Deployment Guide

Phi-4 is a 14B open-weight model trained for maths and reasoning at small scale.

What is Phi-4?

Phi-4 is a 14B open-weight model trained for maths and reasoning at small scale, published by Microsoft with open weights at microsoft/phi-4. LLM API does not route this model today, so there is no endpoint or code sample for it here. What this page does give you is the self-hosting picture: published weight sizes, the VRAM each quantisation needs and the commands to serve it yourself. Every figure is read from the public repository and refreshed weekly.

How to run Phi-4 yourself

Open weights (mit), 14.7B parameters. Below: how much memory the weights need at each quantization, which hardware fits them, and the commands to serve it.

Phi-4 VRAM requirements

Precision / quantizationWeightsFigureSource
BF16 (full precision)29.3 GBEstimate14.7B params × 2 bytes
FP815.7 GBFile sizeRedHatAI/phi-4-FP8-dynamic
AWQ 4-bit9.1 GBFile sizestelterlab/phi-4-AWQ

File size = actual download size on Hugging Face. Estimate = parameter count × bytes per weight. Weights only — the KV cache for long contexts needs extra memory; the fit tables below add 15% headroom as a rule of thumb.

GPU requirements: deploy Phi-4 on your hardware

HardwareBF16 (full precision)FP8AWQ 4-bit
NVIDIA H200141 GB
NVIDIA H10080 GB
NVIDIA A100 80GB80 GB
NVIDIA L40S48 GB

GPUs needed per variant.

HardwareBF16 (full precision)FP8AWQ 4-bit
AWS p5.48xlarge8× H100 · 640 GBFitsFitsFits
AWS p4de.24xlarge8× A100 80GB · 640 GBFitsFitsFits
AWS g6e.12xlarge4× L40S · 192 GBFitsFitsFits
Google Cloud a3-highgpu-8g8× H100 · 640 GBFitsFitsFits
Azure ND H100 v58× H100 · 640 GBFitsFitsFits

Whole-instance GPU memory; public instance specs.

Serve it yourself

pip install -U vllm
vllm serve microsoft/phi-4
pip install 'sglang[all]'
python -m sglang.launch_server --model-path microsoft/phi-4

Commands use the official repositories above; vLLM and SGLang expose an OpenAI-compatible endpoint.

Not on LLM.API yet

We do not route this model through our API at the moment. Browse the models you can call today — most workloads have a close match already live.

Not available on LLM API yet

We do not route this model through our API at the moment, so there is no endpoint or code snippet for it yet. Browse the models you can call today — most workloads have a close match already live.

Browse available models

Why run Phi-4 on LLM.API?

  • Unified AI Routing

    Reach Phi-4 and sibling models through one OpenAI-compatible endpoint.

  • Cost Control

    Production: Compare provider price points and keep spend visible as you scale Phi-4.

  • Reliability Layer

    Retry and route across configured providers when a single upstream blips.

  • Observability

    Trace prompts, tokens, and errors for Phi-4 alongside the rest of your stack.

  • Drop-in SDKs

    Keep using familiar OpenAI client patterns with base URL https://api.llmapi.ai/v1.

  • Model Breadth

    Swap Phi-4 for chat, media, or embedding alternatives without rewriting auth.

When to Use — When NOT to Use

Get one key to every model

Swap your API key. Keep your code.