RunAnywhere AI

Chat

CPU starting…

On-device models — download, load, and manage storage. Nothing leaves your machine.

Add any model

Load any compatible model by HuggingFace repo, direct URL, or local file path.

Source

Type Language (chat)Vision-languageEmbeddingsSpeech-to-textText-to-speech Add

Examples: unsloth/gemma-3-1b-it-GGUF · https://huggingface.co/owner/repo (paste the page URL) · https://…/model.gguf · C:\models\model.gguf. GGUF + mmproj are auto-resolved for vision models.

Generation defaults and secure credentials.

System prompt

Temperature · 0.3

Max tokens

Reasoning mode — ask the model to think step by step; its reasoning shows in a collapsible block, separate from the answer. Save settings

API key

Stored encrypted with Windows DPAPI.

Save key

Compute device

Inference runs on the CPU in this build. A CUDA (NVIDIA GPU) build is available — launch with RunAnywhere AI (GPU).cmd.

Extract typed JSON — decoding is grammar-constrained, so the output always parses.

Ada Lovelace was a 36 year old English mathematician who loved poetry. Extract

Result

The model picks a tool and fills its arguments.

What time is it right now? Choose tool

Result

Describe an image with the vision-language model.

Choose imageNo image selected

Caption

Caption

Semantic similarity — cosine distance between two sentence embeddings.

Compare

Result

Add documents, then ask questions answered only from what you added.

Add a document

Add to knowledgeClear all

Ask a question

Ask

Answer

Tap to talk

Speech, reasoning and speech-synthesis all run on this device.

You

RunAnywhere

Stop automatically when I stop speaking

Built-in energy VAD. Hold and speak — the first ~2s calibrate ambient noise.

Threshold · 0.015

Hold + speak

Result