Model Summary

Phi-4-mini-instruct is a lightweight open model built upon synthetic data and filtered publicly available websites - with a focus on high-quality, reasoning dense data. The model belongs to the Phi-4 model family and supports 128K token context length. The model underwent an enhancement process, incorporating both supervised fine-tuning and direct preference optimization to support precise instruction adherence and robust safety measures.

📰 Phi-4-mini Microsoft Blog 📖 Phi-4-mini Technical Report 👩‍🍳 Phi Cookbook 🏡 Phi Portal 🖥️ Try It Azure, Huggingface

Phi-4: [mini-instruct | onnx]; multimodal-instruct; gguf

Usage

Chat format

This format is used for general conversation and instructions:

<|system|>Insert System Message<|end|><|user|>Insert User Message<|end|><|assistant|>

Tool-Enabled Function-Calling Format

This format is used when the user wants the model to provide function calls based on the given tools. The user should define the available tools in the system prompt, wrapped by <|tool|> and <|/tool|> tokens. The tools must be specified in JSON format using a structured JSON dump.

<|system|>
You are a helpful assistant with some tools.
<|tool|>
[
  {
    "name": "get_weather_updates",
    "description": "Fetches weather updates for a given city using the RapidAPI Weather API.",
    "parameters": {
      "city": {
        "description": "The name of the city for which to retrieve weather information.",
        "type": "str",
        "default": "London"
      }
    }
  }
]
<|/tool|>
<|end|>

<|user|>
What is the weather like in Paris today?
<|end|>

<|assistant|>

Unsloth Bug Fixes for Better Performance

Update (March 1, 2025)

Applying all Unsloth fixes improved inference stability.

🚀 Phi 4 Mini Function Calling Test!

If you have a minute, I’d really appreciate it if you could test my Phi-4-Mini-Instruct Demo at 👉 Quantum Network Monitor.
💬 Click the chat icon (bottom right of the main and dashboard pages) . Then toggle between the LLM Types Phi-4-Mini-Instruct is called TestLLM : TurboLLM -> FreeLLM -> TestLLM.

What I'm Testing

I'm experimenting with function calling against my network monitoring service. Using small open source models. I am into the question "How small can it go and still function". 🟡 TestLLM – Runs Phi-4-mini-instruct using phi-4-mini-q4_0.gguf , llama.cpp on 6 threads of a Cpu VM (Should take about 15s to load. Inference speed is quite slow and it only processes one user prompt at a time—still working on scaling!). If you're curious, I'd be happy to share how it works! .

The other Available AI Assistants

🟢 TurboLLM – Uses gpt-4o-mini Fast! . Note: tokens are limited since OpenAI models are pricey, but you can Login or Download the Quantum Network Monitor agent to get more tokens, Alternatively use the TestLLM .
🔵 HugLLM – Runs open-source Hugging Face models Fast, Runs small models (≈8B) hence lower quality, Get 2x more tokens (subject to Hugging Face API availability)

Phi-4-mini-instruct GGUF Models

Choosing the Right Model Format

Selecting the correct model format depends on your hardware capabilities and memory constraints.

BF16 (Brain Float 16) – Use if BF16 acceleration is available

• A 16-bit floating-point format designed for faster computation while retaining good precision.
• Provides similar dynamic range as FP32 but with lower memory usage.
• Recommended if your hardware supports BF16 acceleration (check your device’s specs).
• Ideal for high-performance inference with reduced memory footprint compared to FP32.

📌 Use BF16 if:
✔ Your hardware has native BF16 support (e.g., newer GPUs, TPUs).
✔ You want higher precision while saving memory.
✔ You plan to requantize the model into another format.

📌 Avoid BF16 if:
❌ Your hardware does not support BF16 (it may fall back to FP32 and run slower).
❌ You need compatibility with older devices that lack BF16 optimization.

F16 (Float 16) – More widely supported than BF16

• A 16-bit floating-point high precision but with less of range of values than BF16.
• Works on most devices with FP16 acceleration support (including many GPUs and some CPUs).
• Slightly lower numerical precision than BF16 but generally sufficient for inference.

📌 Use F16 if:
✔ Your hardware supports FP16 but not BF16.
✔ You need a balance between speed, memory usage, and accuracy.
✔ You are running on a GPU or another device optimized for FP16 computations.

📌 Avoid F16 if:
❌ Your device lacks native FP16 support (it may run slower than expected).
❌ You have memory limtations.

Quantized Models (Q4_K, Q6_K, Q8, etc.) – For CPU & Low-VRAM Inference

Quantization reduces model size and memory usage while maintaining as much accuracy as possible.

• Lower-bit models (Q4_K) → Best for minimal memory usage, may have lower precision.
• Higher-bit models (Q6_K, Q8_0) → Better accuracy, requires more memory.

📌 Use Quantized Models if:
✔ You are running inference on a CPU and need an optimized model.
✔ Your device has low VRAM and cannot load full-precision models.
✔ You want to reduce memory footprint while keeping reasonable accuracy.

📌 Avoid Quantized Models if:
❌ You need maximum accuracy (full-precision models are better for this).
❌ Your hardware has enough VRAM for higher-precision formats (BF16/F16).

Summary Table: Model Format Selection

Included Files & Details

phi-4-mini-bf16.gguf

• Model weights preserved in BF16.
• Use this if you want to requantize the model into a different format.
• Best if your device supports BF16 acceleration.

phi-4-mini-f16.gguf

• Model weights stored in F16.
• Use if your device supports FP16, especially if BF16 is not available.

phi-4-mini-bf16-q8.gguf

• Output & embeddings remain in BF16.
• All other layers quantized to Q8_0.
• Use if your device supports BF16 and you want a quantized version.

phi-4-mini-f16-q8.gguf

• Output & embeddings remain in F16.
• All other layers quantized to Q8_0.

phi-4-mini-q4_k_l.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q4_K.
• Good for CPU inference with limited memory.

phi-4-mini-q4_k_m.gguf

• Similar to Q4_K.
• Another option for low-memory CPU inference.

phi-4-mini-q4_k_s.gguf

• Smallest Q4_K variant, using less memory at the cost of accuracy.
• Best for very low-memory setups.

phi-4-mini-q6_k_l.gguf

• Output & embeddings quantized to Q8_0.
• All other layers quantized to Q6_K .

phi-4-mini-q6_k_m.gguf

• A mid-range Q6_K quantized model for balanced performance .
• Suitable for CPU-based inference with moderate memory.

phi-4-mini-q8.gguf

• Fully Q8 quantized model for better accuracy.
• Requires more memory but offers higher precision.

Credits

Thanks Bartowski for imartix upload. And your guidance on quantization that has enabled me to produce these gguf file.

Thanks Unsloth for bug fixing many models.

Thanks for your support! 🙌