Phi 4 Mini Instruct is an open-source language model by unsloth. Features: 3.8b LLM, VRAM: 7.7GB, Context: 128K, License: mit, Instruction-Based, LLM Explorer Score: 0.23.
Base model:finetune:microsoft/... Base model:microsoft/phi-4-min... Chat Code Conversational Custom code Endpoints compatible Instruct Math Microsoft Multilingual Phi Phi3 Phi4 Region:us Safetensors Sharded Tensorflow Unsloth
Model Card on HF 🤗: https://huggingface.co/unsloth/Phi-4-mini-instruct
Phi 4 Mini Instruct Benchmarks
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)
Phi 4 Mini Instruct Parameters and Internals
| LLM Name | Phi 4 Mini Instruct |
| Repository 🤗 | https://huggingface.co/unsloth/Phi-4-mini-instruct |
| Base Model(s) | |
| Model Size | 3.8b |
| Required VRAM | 7.7 GB |
| Updated | 2026-04-21 |
| Maintainer | unsloth |
| Model Type | phi3 |
| Instruction-Based | Yes |
| Model Files | |
| Model Architecture | Phi3ForCausalLM |
| License | mit |
| Context Length | 131072 |
| Model Max Length | 131072 |
| Transformers Version | 4.49.0 |
| Tokenizer Class | GPT2Tokenizer |
| Padding Token | <｜PAD▁TOKEN｜> |
| Vocabulary Size | 200064 |
| Torch Data Type | bfloat16 |
Best Alternatives to Phi 4 Mini Instruct
Best Alternatives |
Context / RAM |
Downloads |
Likes |
|---|---|---|---|
| Phi 3.5 Mini Instruct | 128K / 7.7 GB | 291298 | 909 |
| Phi 4 Mini Instruct Heretic | 128K / 7.7 GB | 423 | 0 |
| MediPhi Instruct | 128K / 7.7 GB | 2709 | 66 |
| Phi 3 Mini 128K Instruct | 128K / 7.7 GB | 5 | 0 |
| NuExtract V1.5 | 128K / 7.7 GB | 108511 | 89 |
| Phi 3.5 Mini TitanFusion 0.1 | 128K / 7.7 GB | 18 | 0 |
| ECE EIFFEL 3Bv2 | 128K / 7.7 GB | 9 | 0 |
| MediPhi Clinical | 128K / 7.7 GB | 512 | 14 |
| MediPhi MedCode | 128K / 7.7 GB | 310 | 7 |
| MediPhi PubMed | 128K / 7.7 GB | 208 | 11 |
Note: green Score (e.g. "73.2") means that the model is better than unsloth/Phi-4-mini-instruct .
Rank the Phi 4 Mini Instruct 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? 53185 in total.
Original data from HuggingFace, OpenCompass and various public git repos.
Check out Ag3ntum — our secure, self-hosted AI agent for server management.
Release v20260328a