byteshape author hub
Qwen3.8 27B GGUF ShapeLearn Lite Quantized This is a GGUF quantized version of Qwen3.8 27B produced with ShapeLearn Lite , a faster variant of ByteShape's ShapeLearn algorithm that learns the datatype for each tensor. With our current compute allocation, ShapeLearn Lite enabled …
Models
2
Downloads
0
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.