Qwen3.8-27B Multimodal Reasoning Model Released in GGUF Format

empero-ai · hf · 2026-08-17

The Qwen3.8-27B-Ridge-GGUF model is released, featuring an image-text-to-text pipeline. Quantized for llama.cpp compatibility, it is based on the Qwen3.8 architecture and targets multimodal reasoning tasks.

Original post →

More from Models

Models channel →