QQZ2026 author hub
Qwen3.8 27B LowDrift UD IQ4 XS + Embedded MTP GGUF Low drift / reduced refusal Qwen3.8 27B derivative using an earlier Unsloth UD IQ4 XS preview era tensor layout and an embedded original MTP layer, packaged as GGUF for llama.cpp. Quantization provenance note: the 13.274 GiB UD …
Models
4
Downloads
0
Run models locally with guIDE
Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.