Microsoft - Dense - verified
Run Phi-4-reasoning-plus locally
Phi-4-reasoning-plus is a 14.7B dense model from Microsoft with a 33K-token context window, released under MIT (commercial use is allowed); the smallest listed download is 9.1 GB, the Q4_K_M GGUF build from unsloth/Phi-4-reasoning-plus-GGUF.
Official weights: microsoft/Phi-4-reasoning-plus
- Total params
- 14.7B
- Architecture
- Dense
- Context
- 33K
- Smallest download
- 9.1 GB
Fits in
Smallest download at most 85% of memoryDownloads
The official weights and every quantization listed for this model, with file sizes from Hugging Face.
| Download | Format | Size | Repo |
|---|---|---|---|
Official weights | BF16 | 29.3 GB | microsoft/Phi-4-reasoning-plus |
Q4_K_MSmallest listed | GGUF | 9.1 GB | unsloth/Phi-4-reasoning-plus-GGUF |
Q8_0 | GGUF | 15.6 GB | unsloth/Phi-4-reasoning-plus-GGUF |
4bit | MLX | 9.2 GB | mlx-community/Phi-4-reasoning-plus-4bit |
GB is decimal: 1 GB = 10^9 bytes. Add memory for the context and the operating system on top of the file size.
Run it
Copied verbatim from the page linked under each command. Server commands from model cards often assume a multi-GPU node; check the flags before you run them.
vLLM
vllm serve microsoft/Phi-4-reasoning-plus --enable-reasoning --reasoning-parser deepseek_r1Not sure which runtime to use? Compare local LLM runtimes by platform, API and features.
License
- License
- MIT
mit - Commercial use
- Commercial use: YesCommercial use is allowed.
- Gated download
- No. The files download directly.
Worth knowing
Reasoning fine-tune of the Phi-4 base with a 32k context, and the card's vLLM command uses the deepseek_r1 reasoning parser.
Released (per the model card).
FAQ
How big is the Phi-4-reasoning-plus download?
The official BF16 weights in microsoft/Phi-4-reasoning-plus are 29.3 GB. The smallest listed download is 9.1 GB, the Q4_K_M GGUF build from unsloth/Phi-4-reasoning-plus-GGUF. Plan for more memory than the file size: the context (KV cache) and the operating system need room too.
Can I use Phi-4-reasoning-plus commercially?
Phi-4-reasoning-plus is released under MIT, and commercial use is allowed. The license text is at https://huggingface.co/microsoft/Phi-4-reasoning-plus/blob/main/LICENSE.
How much memory do I need for Phi-4-reasoning-plus?
By this directory's rule of thumb it fits in 16 GB and up: the smallest listed download, 9.1 GB, is at most 85% of 16 GB, which leaves room for the context and the operating system.
How do I run Phi-4-reasoning-plus with Ollama?
Run "ollama run phi4-reasoning:plus", as shown at https://ollama.com/library/phi4-reasoning. The Ollama library lists the phi4-reasoning:plus tag at 11GB.
What is the context length of Phi-4-reasoning-plus?
32,768 tokens. A longer context needs more memory for the KV cache, so you can run with a shorter one when memory is tight.
Sources
Last verified from the pages below.
- HF API - huggingface.co
- HF file tree - huggingface.co
- Model card - huggingface.co
- Ollama phi4-reasoning - ollama.com
Newsletter
New open weights, every week
One email per week. New model releases, open-weight drops and what they mean for what you build.
Keep exploring
Best local AI models
Our curated picks by hardware tier, with benchmarks and the reasoning.
Model API pricing and specs
First-party prices per 1M tokens when you would rather call an API.
AI benchmark leaderboards
Sourced scores, for when you need to compare quality.
Setup guides
Point your coding tools at the model you picked.