| library_name: gguf | |
| pipeline_tag: image-text-to-text | |
| tags: [gguf, rocmfpx, rocmfp4, amd, rocm, strix-halo, qwen, qwen4, coming-soon] | |
| # Qwen4-Flash-Next — ROCmFPX GGUF (coming soon) | |
| **This repo has no files yet.** | |
| Qwen 4 Flash Next is expected to be released in the next few days. As soon as it is out, its ROCmFPX quants will be | |
| uploaded here, built for AMD GPUs and Strix Halo with the [ROCmFPX](https://github.com/HarshaVardhan3002/ROCmFPX) | |
| llama.cpp fork. | |
| The planned ROCmFPX quants of [Qwen/Qwen3.8-Flash-Next](https://huggingface.co/Qwen/Qwen3.8-Flash-Next) were stopped | |
| in favour of this model. | |
| Follow this account to get the files when they are up. | |