---
license: cc-by-4.0
base_model: ManniX-ITA/Qwen3.6-27B-A3B-Coder
tags:
- gguf
- rocm
- rocmfpx
- amd
- llama.cpp
---

# Qwen3.6-27B-A3B-Coder-ROCMFP4_FAST - ROCmFPX Quantized

This model was dynamically quantized and generated using the [ROCmFPX My Repo Space](https://huggingface.co/spaces/alst10/ROCmFPX-my-repo)
* **Original Base Model:** [ManniX-ITA/Qwen3.6-27B-A3B-Coder](https://huggingface.co/ManniX-ITA/Qwen3.6-27B-A3B-Coder)

## Usage Instructions with ROCmFPX llama.cpp

To run this model, you must use the specialized [ROCmFPX fork of llama.cpp](https://github.com/charlie12345/ROCmFPX) by charlie12345. Standard `llama.cpp` releases do not currently support ROCmFPX quantization formats.

```bash
# 1. Clone the ROCmFPX repository
git clone --depth 1 [https://github.com/charlie12345/ROCmFPX.git](https://github.com/charlie12345/ROCmFPX.git)
cd ROCmFPX

# 2. Build the project
cmake -B build -G Ninja -DGGML_CUDA=OFF -DGGML_NATIVE=OFF
cmake --build build --target llama-cli -j

# 3. Run the model
./build/bin/llama-cli -m Qwen3.6-27B-A3B-Coder-Q4_0_ROCMFP4_FAST.gguf -p "You are a helpful assistant. Hello!" -n 128
```

## License
This model is distributed under the [Creative Commons Attribution 4.0 International (CC BY 4.0)](https://creativecommons.org/licenses/by/4.0/) license. Please adhere to the original license constraints of the base model and provide appropriate attribution when sharing.