Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF

Description

Qwen3.8-27B-DFlash2-ROCmFP4-FAST-GGUF is an open-weight text-generation model with roughly 27B parameters published by agentionai on the Hugging Face Hub. It has 2,812 downloads.

Categories

• Coding
• Productivity

Tags

• dflash2
• speculative-decoding
• draft-model
• rocmfp4
• vulkan
• strix-halo
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• 27B parameters