gemma-3-12b-it-ONNX-WebGPU

google/gemma-3-12b-it converted to ONNX for running in a web browser with ONNX Runtime Web's WebGPU backend, as used by Quick Inference.

Changes from the original

• Converted to an ONNX decoder in ONNX Runtime GenAI's layout (input_ids, attention_mask, past_key_values.* → logits, present.*) by Quick Inference's own exporter, with the rotary embedding inside GroupQueryAttention.
• Linear layers and the LM head are quantised to 4 bits (round to nearest, block size 32). Embeddings, activations and the KV cache are float16.
• Only the language model is converted (the vision tower is left out): text in, text out.

These are modified files: their outputs are close to, but not identical to, the original model's.

Use restrictions

Gemma is provided under and subject to the Gemma Terms of Use (GEMMA_TERMS_OF_USE.md). By using these files you agree to those terms, including the use restrictions in their section 3.2: you may not use these files or anything made from them for the restricted uses in the Gemma Prohibited Use Policy (GEMMA_PROHIBITED_USE_POLICY.md). If you distribute them or anything made from them, you must pass these restrictions on in the same way.

Licence

Licensed under the same terms as the original model: see GEMMA_PROHIBITED_USE_POLICY.md, GEMMA_TERMS_OF_USE.md, NOTICE.