Phi 4 By microsoft: Benchmarks, Features and Detailed Analysis. Insights on Phi 4.

Arxiv:2412.08905 Autotrain compatible Chat Code Conversational En Endpoints compatible Math Phi Phi3 Region:us Safetensors Sharded Tensorflow

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

Phi 4 Benchmarks

LMSys ELO: 1221 vs 1272 (so35)^-4%

IFEval: 5.85 vs 88 (so35)^-93.4%

MATH Lvl 5: 31.65

LLME Score: 0.62894

^nn.n% — How the model compares to the reference models: Anthropic Sonnet 3.5 ("so35"), GPT-4o ("gpt4o") or GPT-4 ("gpt4").

What is the LLM Explorer Rank (Score)

🌟 Advertise your project 🚀

Phi 4 Parameters and Internals

LLM Name	Phi 4
Repository 🤗	https://huggingface.co/microsoft/phi-4
Model Size	14.7b
Required VRAM	29.4 GB
Updated	2025-07-24
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	16384
Model Max Length	16384
Transformers Version	4.47.0
Tokenizer Class	GPT2Tokenizer
Padding Token	<\|dummy_85\|>
Vocabulary Size	100352
Torch Data Type	bfloat16

Quantized Models of the Phi 4

Model	Likes	Downloads	VRAM
Phi 4 Unsloth Bnb 4bit	62	42890	10 GB
Phi 4 Bnb 4bit	16	6726	9 GB
Parm 2 CoT 14B 16K O1 QwQ	7	17	29 GB
...perThoughts CoT 14B 16K O1 QwQ	6	265	29 GB
Phi 4 GGUF	4	200545	5 GB
Phi 4 4bit	19	1169	8 GB
Phi 4 8bit	12	1059	15 GB
Phi 4 6bit	6	52	11 GB

Best Alternatives to Phi 4

Best Alternatives	Context / RAM	Downloads	Likes
Phi 4 Reasoning Plus	32K / 29.4 GB	11063	312
Phi 4 Reasoning	32K / 29.4 GB	8826	199
Phi 4 Reasoning Plus	32K / 29.4 GB	1006	4
Flashlight V1.1	16K / 29.4 GB	5	0
Microsoft Phi 4	16K / 29.4 GB	927	56
Phi 4 RP V0	16K / 29.5 GB	6	3
Phi4 Abliterated	16K / 29.4 GB	5	12
Phi 4 AbliteratedRP	16K / 29.5 GB	3	5
Phi 4 Abliterated	16K / 29.4 GB	41	31
DNA R1	16K / 29.4 GB	2947	39

Rank the Phi 4 Capabilities

🆘 Have you tried this model? Rate its performance. This feedback would greatly assist ML community in identifying the most suitable model for their needs. Your contribution really does make a difference! 🌟

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

What open-source LLMs or SLMs are you in search of? 50035 in total.

Email us: info@extractum.io. Our Privacy Policy | Terms and Conditions | Suggest an improvement.

Our Social Media →

Original data from HuggingFace, OpenCompass and various public git repos.

Release v20241124

Support LLM Explorer