qwen3.5-0.8B-CoreAI / gpu-pipelined

Commit History

Upload folder using huggingface_hub
95388e0
verified

mlboydaisuke commited on

qwen3.5-0.8B int8lin decode-only loop-free bundle (pipelined engine): Mac 204 tok/s, iPhone 50.3-51.5 tok/s
0019cb6
verified

mlboydaisuke commited on