Add config.json (HF download-stat query file)

docs: update README with verified complete weights and make -j4 build recipe

docs: update README with verified complete weights and make -j4 build recipe

Upload full Qwen3.8-27B-Splash-HQ native 8-bit model weights

Update README with Q8 engine requirements and upload status notice

Update README with Q8 engine requirements and upload status notice

Upload tokenizer/vocab.json with huggingface_hub

Upload tokenizer/chat_template.jinja with huggingface_hub

Upload tokenizer/tokenizer.json with huggingface_hub

Upload tokenizer/config.json with huggingface_hub

Upload tokenizer/tokenizer_config.json with huggingface_hub

Upload manifest.json with huggingface_hub

Initial model card and benchmark documentation

initial commit