Qwen3.8-27B-MTP-Q3_0_ROCMFPX

Description

Qwen3.8-27B-MTP-Q3_0_ROCMFPX is an open-weight text-generation model with roughly 27B parameters published by pugant on the Hugging Face Hub. It has 224 downloads. Runs with llama.cpp.

Categories

• Productivity

Tags

• llama.cpp
• rocmfpx
• gfx1151
• strix-halo
• qwen35
• dense
• mtp
• gated-deltanet

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: llama.cpp
• 27B parameters