AI가 움직이고 미래가 업데이트됩니다.Qwen3-0.6B
This repository contains LiteRT-LM variants of Qwen3-0.6B for Android and desktop deployment. The mixed INT4 `.litertlm` artifact was produced with a TorchAO-based quantize-first recipe from the original Hugging Face checkpoint. This is a mixed quantization layout rather than a uniform all-INT4 model: eligible linear projection weights are stored as blockwise INT4 with group size 32 and floating-point scales, token embedding weights use weight-only INT8 quantization, and normalization/reduction paths plus KV cache tensors remain floating point. The mixed INT4 bundle also uses LiteRT-LM StableHLO composite ops for attention/cache execution, including `odml.runtime_bmm` and `odml.cache_update`.
번역 준비 중입니다. 원문을 표시합니다.
This repository contains LiteRT-LM variants of Qwen3-0.6B for Android and desktop deployment. The mixed INT4 `.litertlm` artifact was produced with a TorchAO-based quantize-first recipe from the original Hugging Face checkpoint. This is a mixed quantization layout rather than a uniform all-INT4 model: eligible linear projection weights are stored as blockwise INT4 with group size 32 and floating-point scales, token embedding weights use weight-only INT8 quantization, and normalization/reduction paths plus KV cache tensors remain floating point. The mixed INT4 bundle also uses LiteRT-LM StableHLO composite ops for attention/cache execution, including `odml.runtime_bmm` and `odml.cache_update`.