nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 download history
nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 is an 18.2B-parameter text generation model by nvidia. In the last 30 days it was downloaded 1,265,547 times (338,506 in the last 7 days), and 6,329,400 times in total.
It ranks #318 on the Hub by monthly downloads and #62 among text generation models.
It has 180 likes.
It is a quantization of nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.
7 models build on NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4: 3 quantized, 0 fine-tuned, 4 adapters and 0 merges. Together with the original they were downloaded 1,266,716 times in the last 30 days. See the NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 galaxy.
Most downloaded derivatives
- unsloth/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 (quantized), 463 downloads in 30 days
- mlx-community/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 (quantized), 431 downloads in 30 days
- FedericoFB/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4-GGUF (quantized), 218 downloads in 30 days
- uditjain/Nemotron-30B-Code-Instruct-LoRI (adapter), 27 downloads in 30 days
- uditjain/Nemotron-30B-Multi-Domain-DARE-TIES-Merged-LoRI (adapter), 21 downloads in 30 days
- uditjain/Nemotron-30B-Science-Instruct-LoRI (adapter), 9 downloads in 30 days
- uditjain/Nemotron-30B-Math-Instruct-LoRI (adapter), 0 downloads in 30 days
Open nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-NVFP4 on Hugging Face