nvidia/NVIDIA-Nemotron-Nano-9B-v2 download history
nvidia/NVIDIA-Nemotron-Nano-9B-v2 is an 8.9B-parameter text generation model by nvidia. In the last 30 days it was downloaded 333,618 times (77,860 in the last 7 days), and 4,439,776 times in total.
It ranks #1,065 on the Hub by monthly downloads and #261 among text generation models.
It has 522 likes, 2 of them in the last week.
It is a fine-tune of nvidia/NVIDIA-Nemotron-Nano-12B-v2.
172 models build on NVIDIA-Nemotron-Nano-9B-v2: 97 quantized, 58 fine-tuned, 16 adapters and 1 merges. Together with the original they were downloaded 4,110,226 times in the last 30 days. See the NVIDIA-Nemotron-Nano-9B-v2 galaxy.
Most downloaded derivatives
- nvidia/NVIDIA-Nemotron-3-Nano-4B-BF16 (finetune), 3.4M downloads in 30 days
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-FP8 (finetune), 208.6K downloads in 30 days
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-NVFP4 (finetune), 11.2K downloads in 30 days
- bartowski/nvidia_NVIDIA-Nemotron-Nano-9B-v2-GGUF (quantized), 7.6K downloads in 30 days
- nvidia/NVIDIA-NemotronLabs-VoiceChat-11B (finetune), 4K downloads in 30 days
- nvidia/NVIDIA-Nemotron-Nano-9B-v2-Japanese (finetune), 3.5K downloads in 30 days
- cyankiwi/NVIDIA-Nemotron-Nano-9B-v2-AWQ-4bit (quantized), 1.2K downloads in 30 days
- gaianet/NVIDIA-Nemotron-Nano-9B-v2-GGUF (quantized), 736 downloads in 30 days
- dominguesm/NVIDIA-Nemotron-Nano-9B-v2-GGUF (quantized), 725 downloads in 30 days
- eaddario/IQ2_NL-IQ3_NL-Test-Models (quantized), 576 downloads in 30 days
- mlx-community/NVIDIA-Nemotron-Nano-9B-v2-4bits (finetune), 562 downloads in 30 days
- second-state/NVIDIA-Nemotron-Nano-9B-v2-GGUF (quantized), 497 downloads in 30 days