NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-MTPv2-layers

Description

NVIDIA-Nemotron-3-Super-120B-A12B-UD-Q4_K_XL-MTPv2-layers is an open-weight text-generation model with roughly 120B parameters published by meshllm on the Hugging Face Hub. It has 1,291 downloads. Runs with mesh-llm.

Categories

• Productivity

Tags

• mesh-llm
• layer-package
• skippy
• distributed-inference
• local-inference
• openai-compatible
• text-generation
• imatrix

Capabilities

• Text generation
• Conversational
• GGUF quantised builds
• Library: mesh-llm
• 120B parameters