Spaces:
Build error
Build error
| title: Mobile LLM Leaderboard | |
| emoji: 🏆 | |
| colorFrom: blue | |
| colorTo: green | |
| sdk: gradio | |
| sdk_version: "4.44.0" | |
| app_file: app.py | |
| pinned: true | |
| license: apache-2.0 | |
| tags: | |
| - leaderboard | |
| - mobile | |
| - llm | |
| - on-device | |
| - benchmark | |
| - dispatchai | |
| # 🏆 dispatchAI Mobile LLM Leaderboard | |
| The definitive leaderboard for mobile-optimized LLMs. | |
| Every model in this leaderboard has been: | |
| - Re-engineered for mobile deployment | |
| - Quantized for on-device constraints (<4GB RAM) | |
| - Tested on real Snapdragon 865 hardware (Samsung S20 FE) | |
| ## Categories | |
| - **Chat** — General instruction-following | |
| - **Code** — Code completion | |
| - **Math** — Mathematical reasoning | |
| - **Arabic** — Arabic language models | |
| - **Function Call** — Tool-use and agent models | |
| - **Vision** — Multimodal image understanding | |
| - **Embedding** — Vector embeddings for RAG | |
| ## Submit Your Model | |
| To submit a model for inclusion, open a discussion on this Space with: | |
| - Model name and HuggingFace link | |
| - Parameter count and size | |
| - Quantization method | |
| - Target hardware | |
| We'll benchmark it on our phone farm and add it to the leaderboard. | |
| ## About dispatchAI | |
| Small. Mobile. Free. UAE-built. 🚀 | |