Experimental model. This repository is an experimental Alkahest/Rally package. It may fail, behave unpredictably, or produce unsuitable output. Use at your own risk; do not rely on it for safety-critical or production decisions without your own validation.

thomasjvu/alkahest-2b-q4-onnx

Private q4 WebGPU ONNX package for the finalized Alkahest 2B direct lane.

Text sessions use official-style q4 artifacts:

  • onnx/embed_tokens_q4.onnx
  • onnx/decoder_model_merged_q4.onnx

This package passed browser text smoke and is kept as the desktop-class direct target.

Downloads last month
13
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support