Mellum2-12B-A2.5B-Instruct-GGUF-MXFP4_MOE

Description

Mellum2-12B-A2.5B-Instruct-GGUF-MXFP4_MOE is an open-weight text-generation model with roughly 12B parameters published by JetBrains on the Hugging Face Hub. It has 400 downloads. Runs with gguf.

Categories

• Productivity

Tags

• mellum
• llama.cpp
• quantized
• moe
• instruct
• text-generation
• en
• conversational

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: gguf
• 12B parameters