Phi-4 Mini

What Phi-4 Mini is for

Phi-4 Mini is a general-purpose open-weights model from Microsoft, released in 2025-02 with a single 3.8B size and 128K of context, licensed MIT. The catalogue records its strength as small chat with function calling and tool use.

Sizes and memory

The 3.8B needs about 3 GB of weights at Q4_K_M. That is the whole range; there is no larger or smaller variant in this record. Recommended VRAM adds roughly half again on top of the weights for the KV cache and the runtime.

Size	Weights at Q4_K_M	Recommended VRAM	Smallest card in our guide that holds it
3.8B	3 GB	5 GB	NVIDIA Jetson Orin Nano 8GB

Hardware that runs Phi-4 Mini

Every one of the 19 cards with dedicated memory in our hardware guide holds at least one size of Phi-4 Mini at Q4_K_M. The cheapest that does is the NVIDIA Jetson Orin Nano 8GB at about $199, running the 3.8B.

The largest size any of them holds is the 3.8B at 3 GB, on the NVIDIA Jetson Orin Nano 8GB (8 GB at 68 GB/s). Bandwidth, not capacity, sets the speed once a size fits, so a card further down the list with faster memory will generate more tokens per second on the same weights than a larger, slower one.

What people use it for

The catalogue lists 4 recorded uses for Phi-4 Mini: chat, edge, function calling, small. It is tagged chat, tools, function-calling, small.

Where Phi-4 Mini sits in the Phi family

Our catalogue holds 4 Phi entries. Ordered by release date, Phi-4 Mini (2025-02) is the 3rd of them, and Phi-4 Reasoning (2025-04) is newer. Phi-3 carries the same recorded memory footprint, so choosing between it and this one is a question of behaviour rather than of hardware: Phi-4 Mini is the one recorded here for small chat with function calling and tool use.

The MIT licence puts no usage ceiling on it, which matters if the thing you are building has users. That is the practical difference between this and a vendor community licence.

Context window: 128K

128K tokens is roughly 96,000 words at the usual ratio, which is a small repository or a whole book. Two cautions come with a window this size: the KV cache at full length can rival the weights for memory, and models rarely use the far end of their advertised context as well as they use the near end. Treat it as headroom, not as a promise.

How to run Phi-4 Mini locally

Our catalogue does not record registry tags, so look the current tag up in the Ollama library or on Hugging Face before pasting these. The commands below are the shape of the workflow, not a copy-and-paste recipe.

Option 1: Ollama (simplest)

# find the tag for Phi-4 Mini at ollama.com/library
ollama run <tag>

Option 2: Mullama (production)

mullama pull <tag>
mullama run <tag>

Option 3: llama.cpp (CLI)

# download a GGUF from Hugging Face, searching for "Phi-4 Mini GGUF"
./llama-cli -m model.Q4_K_M.gguf -p "Hello, AI!"

Option 4: Python with Mullama or llama-cpp-python

from mullama import Model, Context
model = Model.load("model.Q4_K_M.gguf", n_gpu_layers=99)
ctx = Context(model, n_ctx=4096)
print(ctx.generate("Hello, AI!", 256))

Sources

Model record from src/data/models.json (2026-06-29); card capacities from src/data/gpus.json (2026-06-29). Upstream: Curated from ollama.com/library + community benchmarks + paperswithcode + huggingface.