Nemotron-3-Nano-4B-RotorQuant-MLX-2bit

Description

Nemotron-3-Nano-4B-RotorQuant-MLX-2bit is an open-weight text-generation model with roughly 4B parameters published by majentik on the Hugging Face Hub. It has 438 downloads. Runs with mlx.

Categories

• Coding
• Productivity

Tags

• nemotron_h
• rotorquant
• kv-cache-quantization
• nemotron
• nvidia
• mamba2
• hybrid
• quantized

Capabilities

• Text generation
• Conversational
• Library: mlx
• 4B parameters