--- license: cc-by-4.0 base_model: pragmaticcs/PentaCoder-9B tags: - gguf - rocm - rocmfpx - amd - llama.cpp --- # PentaCoder-9B - ROCmFPX Quantized This repository contains AMD ROCmFPX quantized GGUF weights converted from [pragmaticcs/PentaCoder-9B](https://huggingface.co/pragmaticcs/PentaCoder-9B) using [charlie12345/ROCmFPX](https://github.com/charlie12345/ROCmFPX). ## Available Files | File | Size | Format | | --- | --- | --- | | `PentaCoder-9B-Q4_0_ROCMFP4_FAST.gguf` | 4.44 GB | Q4_0_ROCMFP4_FAST | | `PentaCoder-9B-Q4_0_ROCMFP4.gguf` | 5.47 GB | Q4_0_ROCMFP4 | | `PentaCoder-9B-Q4_0_ROCMFP4_COHERENT.gguf` | 4.95 GB | Q4_0_ROCMFP4_COHERENT | | `PentaCoder-9B-Q4_0_ROCMFP4_FAST_COHERENT.gguf` | 4.72 GB | Q4_0_ROCMFP4_FAST_COHERENT | | `PentaCoder-9B-Q4_0_ROCMFP4_LEAN.gguf` | 4.82 GB | Q4_0_ROCMFP4_LEAN | | `PentaCoder-9B-Q4_0_ROCMFP4_STRIX.gguf` | 4.74 GB | Q4_0_ROCMFP4_STRIX | | `PentaCoder-9B-Q4_0_ROCMFP4_STRIX_LEAN.gguf` | 4.62 GB | Q4_0_ROCMFP4_STRIX_LEAN | | `PentaCoder-9B-Q2_0_ROCMFPX.gguf` | 3.10 GB | Q2_0_ROCMFPX | | `PentaCoder-9B-Q3_0_ROCMFPX.gguf` | 4.60 GB | Q3_0_ROCMFPX | | `PentaCoder-9B-Q6_0_ROCMFPX.gguf` | 6.86 GB | Q6_0_ROCMFPX | | `PentaCoder-9B-Q8_0_ROCMFPX.gguf` | 8.61 GB | Q8_0_ROCMFPX | | `PentaCoder-9B-Q8_0_ROCMFPX_AGENT.gguf` | 8.77 GB | Q8_0_ROCMFPX_AGENT | ## Usage Instructions with ROCmFPX llama.cpp ```bash git clone --depth 1 [https://github.com/charlie12345/ROCmFPX.git](https://github.com/charlie12345/ROCmFPX.git) cd ROCmFPX cmake -B build -G Ninja -DCMAKE_BUILD_TYPE=Release -DGGML_CUDA=OFF -DGGML_NATIVE=ON cmake --build build --target llama-cli -j ./build/bin/llama-cli -m PentaCoder-9B-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.