Back to Runanywhere Sdks

RunAnywhere

examples/electron/RunAnywhereAI/index.html

0.20.122.0 KB
Original Source

Chat

CPUGPU · needs build starting…

Models

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.

Settings

Generation defaults and secure credentials.

System prompt

Temperature · 0.7

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 (Windows DPAPI)

Save key

Compute device

Inference runs on the CPU in this build. A CUDA (NVIDIA GPU) build is available — launch with run-demo-gpu.cmd.

Structured output

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

Tool calling

The model picks a tool and fills its arguments.

What is the weather in Tokyo in celsius? Choose tool

Vision

Describe an image with the vision-language model.

Choose imageNo image selected

Caption

Embeddings

Semantic similarity — cosine distance between two sentence embeddings.

Compare

Knowledge (RAG)

Retrieval-augmented generation — add documents, then ask questions grounded in them. Embeddings (MiniLM) index your text; the LLM answers from the retrieved chunks. First run downloads MiniLM + the chat model.

Add a document

Add to knowledgeClear all

Ask a question

Ask

Voice

Hold to talk — mic → speech-to-text → LLM → text-to-speech → speaker.

Hold to talk Heard

Reply

Voice activity detection

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

Threshold · 0.015

Hold + speak

Detection