Spaces:
Runtime error
Runtime error
| title: GGUF Converter | |
| emoji: 🔄 | |
| colorFrom: blue | |
| colorTo: purple | |
| sdk: gradio | |
| sdk_version: "4.44.0" | |
| app_file: app.py | |
| pinned: false | |
| license: apache-2.0 | |
| tags: | |
| - gguf | |
| - quantization | |
| - converter | |
| - mobile | |
| - dispatchai | |
| # 🔄 dispatchAI GGUF Converter | |
| Convert any HuggingFace model to GGUF format with multiple quantization levels. Free, on ZeroGPU. | |
| ## Features | |
| - **Multiple quant levels**: Q2_K, Q3_K_M, Q4_K_M, Q5_K_M, Q6_K, Q8_0, F16 | |
| - **One-click conversion**: Enter model ID, select quants, click convert | |
| - **Auto-upload**: GGUF files are uploaded directly to the model repo | |
| - **ZeroGPU**: Runs on HuggingFace's free GPU infrastructure | |
| ## Use Cases | |
| - Add GGUF quants to your existing safetensors models | |
| - Create mobile-optimized versions with Q4_K_M (the sweet spot) | |
| - Provide multiple RAM-budget options for your users | |
| 🚀 [dispatchAI](https://huggingface.co/dispatchAI) — Small. Mobile. Free. UAE-built. | |