Model Card on HF 🤗: https://huggingface.co/NyxKrage/Microsoft_Phi-4
Microsoft Phi 4 Benchmarks
MMLU Pro: 47.63
GPQA: 20.81
MUSR: 23.79
BBH: 52.43
IFEval: 5.85 vs 88 (so35)-93.4%
MATH Lvl 5: 29.91
LLME Score: 0.31478
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)
Microsoft Phi 4 Parameters and Internals
| LLM Name | Microsoft Phi 4 |
| Repository 🤗 | https://huggingface.co/NyxKrage/Microsoft_Phi-4 |
| Model Size | 14.7b |
| Required VRAM | 29.4 GB |
| Updated | 2025-09-08 |
| Maintainer | NyxKrage |
| Model Type | phi3 |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| License | other |
| Context Length | 16384 |
| Model Max Length | 16384 |
| Transformers Version | 4.47.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <|endoftext|> |
| Vocabulary Size | 100352 |
| Torch Data Type | bfloat16 |
Best Alternatives to Microsoft Phi 4
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 4 Reasoning | 32K / 29.4 GB | 42235 | 202 |
| Phi 4 Reasoning Plus | 32K / 29.4 GB | 9209 | 322 |
| Phi 4 Reasoning Plus | 32K / 29.4 GB | 1291 | 4 |
| Phi 4 | 16K / 29.4 GB | 1137979 | 2155 |
| Flashlight V1.1 | 16K / 29.4 GB | 6 | 0 |
| Phi 4 RP V0 | 16K / 29.5 GB | 10 | 3 |
| Phi4 Abliterated | 16K / 29.4 GB | 8 | 12 |
| Phi 4 AbliteratedRP | 16K / 29.5 GB | 10 | 5 |
| Phi 4 Abliterated | 16K / 29.4 GB | 28 | 31 |
| DNA R1 | 16K / 29.4 GB | 1900 | 39 |
Note: green Score (e.g. "73.2") means that the model is better than NyxKrage/Microsoft_Phi-4 .
Rank the Microsoft 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! 🌟
What open-source LLMs or SLMs are you in search of? 51191 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Release v20241124