🕯️

Candle Qwen2.5 Instruct

Rust/WASM Demo

The Qwen2.5 models are state-of-the-art multi-language models ranging from 0.5B to 72B parameters. From the benefits of WebAssembly, you can try some of them without LLM servers. For more details of these models, please refer to the technical report.

Note: When first run, the app will download and cache the model, which could take a few minutes.

Models Options:

Advanced Options

Maximum length 512 Temperature 0.00 Top-p 0.90 Repeat Penalty 1.10 Seed

Generation:

No output yet