Qwen3.8 Multimodal Model Released in GGUF Format for Local Inference

HauhauCS · hf · 2026-08-18

HauhauCS released a GGUF version of the Qwen3.8-27B model, a multimodal vision model supporting speculative decoding and FastMTP. The GGUF format facilitates local execution on consumer hardware, optimizing for efficient inference in resource-constrained environments.

Related event: Qwen3.8-27B Multimodal Model Released in GGUF Format for Local Inference(2 posts)→

Original post →

More from Models

Models channel →