Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-6bit

Description

Nemotron-3-Nano-Omni-30B-A3B-Reasoning-TurboQuant-MLX-6bit is an open-weight text-generation model with roughly 30B parameters published by majentik on the Hugging Face Hub. It has 374 downloads. Runs with mlx.

Categories

• Coding
• Research
• Productivity
• Design

Tags

• NemotronH_Nano_Omni_Reasoning_V3
• nemotron
• multimodal
• mamba2
• moe
• quantized
• turboquant
• apple-silicon

Capabilities

• Text generation
• Conversational
• Library: mlx
• 30B parameters