NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ShimQuant-GGUF

Description

NVIDIA-Nemotron-3.5-Lightning-30B-A3B-ShimQuant-GGUF is an open-weight text-generation model with roughly 30B parameters published by BoldingBuilds on the Hugging Face Hub. It has 725 downloads. Runs with gguf.

Categories

• Productivity

Tags

• llama.cpp
• nemotron_h
• moe
• quantization
• imatrix
• text-generation
• conversational

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: gguf
• 30B parameters