GraySoft
Projects Models Compare Cloud benchmarks FAQ Download guIDE →

HermiHg author hub

Qwen3.8 27B DFlash2 — Q2 K S MIX draft half the reference size A mixed precision 2–3 bit quantization of the DFlash 2 draft model for Qwen/Qwen3.8 27B https://huggingface.co/Qwen/Qwen3.8 27B , built to be 50% the size of the reference Q4 K M checkpoint while retaining ~98% of it…

Models
2
Downloads
5,069
HermiHg/Qwen3.8-27B-DFlash2-Q2_K_S-MIX-GGUF
5,069 downloads · text-generation
HermiHg/Qwen3.8-27B-mmproj-Q5_K-MIX-GGUF
0 downloads · image-text-to-text

Run models locally with guIDE

Download guIDE — the AI-native code editor with local LLM inference and 69 built-in tools.

Download guIDE → · Browse 524k+ models · Compare models