Qwen3.8-9B Distill Model Gets GGUF Release for Local Use

A GGUF-quantized distill of Qwen3.8-9B has appeared on Hugging Face, supporting llama.cpp for local deployment, with tags hinting at a gated-deltanet architecture.

2026-08-19 ~ 2026-08-19 · 2 related posts

• Qwen3.8-9B-GGUF released on Hugging Face for local inference — empero-ai · 2026-08-19
• GGUF quantized Qwen3.8-9B-Distill lands for llama.cpp local runs — empero-ai · 2026-08-19