The nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16 galaxy

9 models are built on nvidia/Nemotron-Labs-TwoTower-30B-A3B-Base-BF16: 7 quantized, 2 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 725 times in the last 30 days.

Most downloaded direct derivatives

• pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-bf16 (finetune), 23 downloads in 30 days
• pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-6bit (quantized), 22 downloads in 30 days
• rafaelcaricio/nemotron-twotower-nvfp4 (quantized), 19 downloads in 30 days
• pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-4bit (quantized), 18 downloads in 30 days
• pipenetwork/Nemotron-3-Nano-30B-A3B-context-mlx-8bit (quantized), 17 downloads in 30 days
• pipenetwork/Nemotron-Labs-TwoTower-30B-A3B-mlx-bf16 (finetune), 17 downloads in 30 days
• pipenetwork/Nemotron-Labs-TwoTower-30B-A3B-mlx-4bit (quantized), 14 downloads in 30 days
• pipenetwork/Nemotron-Labs-TwoTower-30B-A3B-mlx-8bit (quantized), 10 downloads in 30 days
• pipenetwork/Nemotron-Labs-TwoTower-30B-A3B-mlx-6bit (quantized), 8 downloads in 30 days

Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.