What are the hardware requirements for Phi 4 Reasoning?

Phi 4 Reasoning requires approximately 29.4 GB of VRAM and supports a context window of 32K tokens. Quantized variants may run on less VRAM; see the Quantized Models section on this page.

Who developed Phi 4 Reasoning and how large is it?

Phi 4 Reasoning is developed by microsoft, a model with 14.7b parameters. The model is published as open weights on Hugging Face and indexed on LLM Explorer with full benchmark history.

Where can I download or evaluate Phi 4 Reasoning?

Phi 4 Reasoning is hosted on Hugging Face and linked from this page. LLM Explorer also lists quantized variants and similar alternatives if available.

Phi 4 Reasoning by microsoft — VRAM 29.4GB, 32K context

Name: Phi 4 Reasoning
Author: microsoft

Phi 4 Reasoning is an open-source language model by microsoft. Features: 14.7b LLM, VRAM: 29.4GB, Context: 32K, License: mit, LLM Explorer Score: 0.24.

Arxiv:2504.21318 Base model:finetune:microsoft/... Base model:microsoft/phi-4 Chat Code Conversational En Endpoints compatible Eval-results Math Phi Phi3 Reasoning Region:us Safetensors Sharded Tensorflow

Model Card on HF 🤗: https://huggingface.co/microsoft/Phi-4-reasoning

Phi 4 Reasoning Parameters and Internals

LLM Name	Phi 4 Reasoning
Repository 🤗	https://huggingface.co/microsoft/Phi-4-reasoning
Base Model(s)	Phi 4 microsoft/phi-4
Model Size	14.7b
Required VRAM	29.4 GB
Updated	2026-07-31
Maintainer	microsoft
Model Type	phi3
Model Files	4.9 GB: 1-of-6 5.0 GB: 2-of-6 4.9 GB: 3-of-6 4.8 GB: 4-of-6 4.8 GB: 5-of-6 5.0 GB: 6-of-6
Supported Languages	en
Model Architecture	Phi3ForCausalLM
License	mit
Context Length	32768
Model Max Length	32768
Transformers Version	4.51.1
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|dummy_85\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Rank the Phi 4 Reasoning capabilities

Have you tried this model? Rate its performance — this feedback helps the ML community find the right model for their needs.

Instruction Following and Task Automation
Factuality and Completeness of Knowledge
Censorship and Alignment
Data Analysis and Insight Generation
Text Generation
Text Summarization and Feature Extraction
Code Generation
Multi-Language Support and Translation

Quantized Models of the Phi 4 Reasoning

Model	Likes	Downloads	VRAM
Phi 4 Reasoning GGUF	23	2768	3 GB

Best Alternatives to Phi 4 Reasoning

Best Alternatives	Context / RAM	Downloads	Likes
Phi 4 Reasoning Plus	32K / 29.4 GB	11601	348
Phi 4 Reasoning	32K / 29.4 GB	126	2
Phi 4 Reasoning Plus	32K / 29.4 GB	73	7
Phi 4	16K / 29.4 GB	670910	2286
Flashlight V1.1	16K / 29.4 GB	5	0
Phi 4 RP V0	16K / 29.5 GB	2	3
Phi4 Abliterated	16K / 29.4 GB	15	12
Microsoft Phi 4	16K / 29.4 GB	74	55
Phi 4 Abliterated	16K / 29.4 GB	16	34
DNA R1	16K / 29.4 GB	21	41

Note: green Score (e.g. "73.2") means that the model is better than microsoft/Phi-4-reasoning.