---
license: mit
language:
- en
base_model:
- unsloth/phi-4
- microsoft/phi-4
pipeline_tag: text-generation
---

# Phi-4 ZeroWw quantizations 

- For q4_k: output and embed tensors quantized to q8_0, all other tensors quantized for q4_k.
- For q5_k, q6_k, q8_0 and q8_0 --pure: output and embed tensors quantized to bf16, all other tensors quantized for q5_k, q6_k, q8_0 and q8_0 --pure.
- BF16 and imatrix for q5_k, q6_k available.

|  | Quant type | File Size | Vram*|
| -------- | ---------- | --------- | -------- |
| [phi-4.q8.q4](https://huggingface.co/cmh/test/blob/main/phi-4.q8.q4.gguf) | 4 bits per weight | 9.43 GB | **12.9 GB** |
| [phi-4.bf16.q5](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.q5.gguf) | 5 bits per weight | 11.9 GB | **14.2 GB** |
| [phi-4.bf16.q5.im](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.q5.im.gguf) | 5 bits per weight | 11.9 GB | **14.2 GB** |
| [phi-4.bf16.q6](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.q6.gguf) | 6 bits per weight | 13.2 GB | **15.5 GB** |
| [phi-4.bf16.q6.im](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.q6.im.gguf) | 6 bits per weight | 13.2 GB | **15.5 GB** |
| [phi-4.bf16.q8](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.q8.gguf) | 8 bits per weight | 16.5 GB | **18.5 GB** |
| [phi-4.bf16.q8p](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.q8p.gguf) | 8 bits per weight | 15.6 GB | **18.6 GB** |
| [phi-4.bf16](https://huggingface.co/cmh/test/blob/main/phi-4.bf16.gguf) | 16 bits per weight | 29.3 GB | tbd |

<sub>*approximate value at **16k context, FP16 cache**.<sup>

---------------------------------------------

[ZeroWw quantization: huggingface.co/RobertSinclair](https://huggingface.co/RobertSinclair) 


```
python convert_hf_to_gguf.py --outtype bf16 phi-4 --outfile phi-4.bf16.gguf

llama-quantize --allow-requantize --output-tensor-type q8_0 --token-embedding-type q8_0 phi-4.bf16.gguf phi-4.q8.q4.gguf q4_k
llama-quantize --allow-requantize --output-tensor-type bf16 --token-embedding-type bf16 phi-4.bf16.gguf phi-4.bf16.q5.gguf q5_k
llama-quantize --imatrix imatrix.dat --leave-output-tensor phi-4.bf16.gguf phi-4.bf16.q5.im.gguf q5_k
llama-quantize --allow-requantize --output-tensor-type bf16 --token-embedding-type bf16 phi-4.bf16.gguf phi-4.bf16.q6.gguf q6_k
llama-quantize --imatrix imatrix.dat --leave-output-tensor phi-4.bf16.gguf phi-4.bf16.q6.im.gguf q6_k
llama-quantize --allow-requantize --output-tensor-type bf16 --token-embedding-type bf16 phi-4.bf16.gguf phi-4.bf16.q8.gguf q8_0
llama-quantize --allow-requantize --pure phi-4.bf16.gguf phi-4.bf16.q8p.gguf q8_0
```

---------------------------------------------

# Phi-4 Model Card 

[Phi-4 Technical Report](https://arxiv.org/pdf/2412.08905)

## Model Summary 

|                         |                                                                               |     
|-------------------------|-------------------------------------------------------------------------------|
| **Developers**          | Microsoft Research                                                            |
| **Description**         | `phi-4` is a state-of-the-art open model built upon a blend of synthetic datasets, data from filtered public domain websites, and acquired academic books and Q&A datasets. The goal of this approach was to ensure that small capable models were trained with data focused on high quality and advanced reasoning.<br><br>`phi-4` underwent a rigorous enhancement and alignment process, incorporating both supervised fine-tuning and direct preference optimization to ensure precise instruction adherence and robust safety measures                |
| **Architecture**        | 14B parameters, dense decoder-only Transformer model                          |
| **Context length**      | 16384 tokens                                                                    |

## Usage

### Input Formats

Given the nature of the training data, `phi-4` is best suited for prompts using the chat format as follows: 

```bash
<|im_start|>system<|im_sep|>
You are a medieval knight and must provide explanations to modern people.<|im_end|>
<|im_start|>user<|im_sep|>
How should I explain the Internet?<|im_end|>
<|im_start|>assistant<|im_sep|>
```