Webml-community runs three Qwen3.5 models locally in browsers with WebGPU
Webml-community's demo runs Alibaba's 0.8B, 2B and 4B multimodal models locally through Transformers.js and WebGPU, with no cloud API required.
By RuntimeWire Staff · Published

Webml-community's demo runs Alibaba's 0.8B, 2B and 4B multimodal models locally through Transformers.js and WebGPU, with no cloud API required.