Phi-4 Reasoning
Phi-4 reasoning and reasoning plus are 14B parameter open-weight reasoning models that rival much larger models on complex reasoning tasks.
What Phi-4 Reasoning is for
Phi-4 Reasoning is a reasoning model: it spends output tokens working through a problem before answering, which makes it slower per useful word and better on problems that need the working shown. Microsoft released it in 2025-04 with a single 14B size under MIT, with a 32K context window. Budget for the extra tokens the thinking phase consumes. The catalogue records its strength as strong reasoning in a 14B model.
Sizes and memory
The 14B needs about 9 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 |
|---|---|---|---|
| 14B | 9 GB | 14 GB | NVIDIA RTX 3060 12GB |
Hardware that runs Phi-4 Reasoning
18 of the 19 cards in our hardware guide hold at least one size of Phi-4 Reasoning at Q4_K_M. The cheapest that does is the NVIDIA RTX 3060 12GB at about $250, running the 14B.
The largest size any of them holds is the 14B at 9 GB, on the NVIDIA RTX 3060 12GB (12 GB at 360 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 3 recorded uses for Phi-4 Reasoning: reasoning, math, small chat. It is tagged reasoning, math, small.
Where Phi-4 Reasoning sits in the Phi family
Our catalogue holds 4 Phi entries. Ordered by release date, Phi-4 Reasoning (2025-04) is the 4th of them, and the most recent. Phi-4 carries the same recorded memory footprint, so choosing between it and this one is a question of behaviour rather than of hardware: Phi-4 Reasoning is the one recorded here for strong reasoning in a 14B model.
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: 32K
32K tokens is about 24,000 words at the usual ratio — enough for a handful of files or a long report held whole. It is the point at which the KV cache starts to be a serious share of memory: doubling the context you actually use costs roughly double the cache, on top of the 9 GB of weights.
How to run Phi-4 Reasoning 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 Reasoning 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 Reasoning 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.