# phimoe_gguf

| | |
|---|---|
| **Model type** | `phimoe_gguf` |
| **Class** | `PhiMoEGGUFCausalLMModel` |
| **Task** | `text-generation` |
| **Source** | `models/moe.py` |

## Description

PhiMoE graph matching llama.cpp's GGUF inference semantics.

The HuggingFace model uses SparseMixer routing, while the pinned llama.cpp
loader uses full softmax followed by normalized top-k routing. GGUF import
therefore uses this internal graph without changing native HF builds.

## Usage

```bash
mobius build --model <MODEL_ID> output_dir/
```

```python
from mobius import build

model = build("<MODEL_ID>")
```