Qwen3.8-27B-heretic-ara-MXFP6-MXFP8-DFlash2-GGUF

Description

Qwen3.8-27B-heretic-ara-MXFP6-MXFP8-DFlash2-GGUF is an open-weight text-generation model with roughly 27B parameters published by sirus on the Hugging Face Hub. It has 651 downloads. Runs with gguf.

Categories

• Coding
• Productivity

Tags

• qwen3.8
• dflash2
• speculative-decoding
• mxfp6
• mxfp8
• blackwell
• llama.cpp
• text-generation

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: gguf
• 27B parameters