Unsloth Nemotron-3 Nano 30B GGUF Model Interface

Model Specifications

Parameters 30B

Quantization A3B

File Size 16.9GB

Context 4096

Min RAM 20GB

Speed ~35 t/s

Generation Settings

Temperature 0.7

Top P 0.9

Max Tokens 512

Repetition Penalty 1.1

Quick Prompts

Unsloth Nemotron-3 Nano Ready

🚀 Welcome to Unsloth Nemotron-3 Nano! I'm a 30B parameter language model optimized for local inference with A3B quantization. I'm here to help with text generation, coding, translation, and more. What can I assist you with today?

Just now