Microsoft·3 sizes·General LLM
Phi models: sizes & hardware to run them
The Phi family spans 3 sizes from 3.8B to 14B. Each size maps to a different hardware tier — below is the approximate memory each needs at 4-bit and the device we’d start with for a private local deployment.
ReasoningCodeMultilingualLong context
Sizes & hardware
| Model | Params | Context | ~VRAM @ 4-bit | Minimum device | Recommended |
|---|---|---|---|---|---|
| Phi-3.5 Mini (3.8B) | 3.8B | 128K | ~2.5GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
| Phi-3 Medium (14B) | 14B | 128K | ~9GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
| Phi-4 (14B) | 14B | 16K | ~9GB | NVIDIA GeForce RTX 3060 12GB | NVIDIA B200 (placeholder) |
Memory figures are approximate working-set estimates (weights + KV cache at modest context); treat as ±. Device picks come from our compatibility engine, best on-prem fit first.
Open each size
General LLM
Phi-3.5 Mini (3.8B)
8GB GPUs, a Mac mini, or even a strong CPU. A small reasoning-leaning model with a permissive MIT license.
General LLM
Phi-3 Medium (14B)
~12GB+ at 4-bit; comfortable on a 16GB GPU or Apple silicon. The MIT license is attractive commercially.
General LLM
Phi-4 (14B)
16GB GPU or Apple silicon at 4-bit. A current small model with strong reasoning and an MIT license.
Run Phi models inside a private AI Business OS
Run your own AI agents on hardware you control — private by design, no per-seat data leaving your premises. BrainOutput helps you pick the right machine and turn it into a working AI Business OS.
Explore the AI Business OS