Qwen3.8 Flash Next GGUF Version Released

AtomicChat · hf · 2026-08-31

AtomicChat released the Qwen3.8-Flash-Next-GGUF model. It is a MoE and multimodal model available in GGUF format for efficient running on llama.cpp, supporting imatrix quantization.

Original post →

More from Models

Models channel →