| --- |
| license: cc-by-4.0 |
| base_model: Cloudflare/clef-flash |
| tags: |
| - gguf |
| - rocm |
| - rocmfpx |
| - amd |
| - llama.cpp |
| --- |
| |
| # cloudflare-clef-flash-ROCmFPX - ROCmFPX Quantized |
| |
| This repository contains AMD ROCmFPX quantized GGUF weights converted from [Cloudflare/clef-flash](https://huggingface.co/Cloudflare/clef-flash) using [charlie12345/ROCmFPX](https://github.com/charlie12345/ROCmFPX). |
| |
| ## Available Files |
| |
| | File | Size | Format | |
| | --- | --- | --- | |
| | `clef-flash-Q4_0_ROCMFP4_FAST.gguf` | 4.44 GB | Q4_0_ROCMFP4_FAST | |
| | `clef-flash-Q4_0_ROCMFP4.gguf` | 5.47 GB | Q4_0_ROCMFP4 | |
| | `clef-flash-Q4_0_ROCMFP4_COHERENT.gguf` | 4.95 GB | Q4_0_ROCMFP4_COHERENT | |
| | `clef-flash-Q4_0_ROCMFP4_FAST_COHERENT.gguf` | 4.72 GB | Q4_0_ROCMFP4_FAST_COHERENT | |
| | `clef-flash-Q4_0_ROCMFP4_LEAN.gguf` | 4.82 GB | Q4_0_ROCMFP4_LEAN | |
| | `clef-flash-Q4_0_ROCMFP4_STRIX.gguf` | 4.74 GB | Q4_0_ROCMFP4_STRIX | |
| | `clef-flash-Q4_0_ROCMFP4_STRIX_LEAN.gguf` | 4.62 GB | Q4_0_ROCMFP4_STRIX_LEAN | |
| | `clef-flash-Q2_0_ROCMFPX.gguf` | 3.10 GB | Q2_0_ROCMFPX | |
| | `clef-flash-Q3_0_ROCMFPX.gguf` | 4.60 GB | Q3_0_ROCMFPX | |
| | `clef-flash-Q6_0_ROCMFPX.gguf` | 6.86 GB | Q6_0_ROCMFPX | |
| | `clef-flash-Q8_0_ROCMFPX.gguf` | 8.61 GB | Q8_0_ROCMFPX | |
| | `clef-flash-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 clef-flash-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. |
| |
