Qwen3.8-9B-GGUF released on Hugging Face for local inference

empero-ai · hf · 2026-08-19

A quantized version of Qwen3.8-9B is trending on Hugging Face, available in GGUF format for llama.cpp compatibility. The model features tags for distillation and reasoning, with gated access via deltanet.

Original post →

More from Models

Models channel →