--- title: Quo AI emoji: 馃敀 colorFrom: indigo colorTo: blue sdk: static app_file: index.html pinned: true license: apache-2.0 short_description: Private AI in your browser. Offline models, no account. models: - unsloth/Qwen3.5-0.8B-GGUF - unsloth/Qwen3.5-2B-GGUF - unsloth/Llama-3.2-3B-Instruct-GGUF - unsloth/gemma-4-E2B-it-qat-GGUF - ggml-org/SmolLM3-3B-GGUF - mistralai/Ministral-3-3B-Instruct-2512-GGUF - unsloth/Phi-4-mini-instruct-GGUF - onnx-community/whisper-base tags: - local-llm - offline - privacy - on-device - webgpu - gguf - llama.cpp - wllama - chat custom_headers: cross-origin-embedder-policy: require-corp cross-origin-opener-policy: same-origin cross-origin-resource-policy: cross-origin --- # Quo AI: private AI in your browser Chat with open models that run **in your browser**, on your own computer. Pick a model, it downloads once from Hugging Face, and from then on it works offline. Nothing you type is sent anywhere. - Qwen3.5 (0.8B, 2B), Llama 3.2 3B, Gemma 4 E2B, SmolLM3 3B, Ministral 3B and Phi-4 Mini, running with [wllama](https://github.com/ngxson/wllama) (llama.cpp in WebAssembly). - Open it full screen on one model: [Qwen3.5 0.8B](https://quo-ai-quo.static.hf.space/?model=qwen35-0.8b) 路 [Qwen3.5 2B](https://quo-ai-quo.static.hf.space/?model=qwen35-2b) 路 [Llama 3.2 3B](https://quo-ai-quo.static.hf.space/?model=llama32-3b) 路 [Gemma 4 E2B](https://quo-ai-quo.static.hf.space/?model=gemma4-e2b) 路 [SmolLM3 3B](https://quo-ai-quo.static.hf.space/?model=smollm3-3b) 路 [Ministral 3B](https://quo-ai-quo.static.hf.space/?model=ministral-3b) 路 [Phi-4 Mini](https://quo-ai-quo.static.hf.space/?model=phi4-mini). Full screen is also faster: models use every processor core there. - Fastest in Chrome and Edge, which use your graphics card. Firefox and Safari run on the processor. - Voice input, also on your computer (Whisper). - No account, no sign-in. This copy runs offline models only. Cloud models, sign-in and Quo Sync are in the full app at [app.quo.computer](https://app.quo.computer/?from=hf-space). **Quo for your computer and phone:** a desktop app for Windows, macOS and Linux (models on your graphics card, any GGUF model from Hugging Face, a coding agent that asks before every change, pictures made on your computer) and an Android app. Get them at [quo.computer](https://quo.computer/?from=hf-space). Open source (Apache 2.0): [github.com/quo-ai/quo](https://github.com/quo-ai/quo).