nvidia/Llama-3.1-Nemotron-70B-Instruct-HF download history
nvidia/Llama-3.1-Nemotron-70B-Instruct-HF is a 70.6B-parameter text generation model by nvidia. In the last 30 days it was downloaded 13,850 times (3,508 in the last 7 days), and 1,944,638 times in total.
It ranks #7,165 on the Hub by monthly downloads and #1,598 among text generation models.
It has 2,071 likes, 1 of them in the last week.
It is a fine-tune of meta-llama/Llama-3.1-70B-Instruct.
1,140 models build on Llama-3.1-Nemotron-70B-Instruct-HF: 695 quantized, 38 fine-tuned, 9 adapters and 398 merges. Together with the original they were downloaded 141,570 times in the last 30 days. See the Llama-3.1-Nemotron-70B-Instruct-HF galaxy.
Most downloaded derivatives
- bartowski/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF (quantized), 2.6K downloads in 30 days
- mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-i1-GGUF (quantized), 1.9K downloads in 30 days
- mlx-community/nvidia_Llama-3.1-Nemotron-70B-Instruct-HF_4bit (quantized), 1.2K downloads in 30 days
- mradermacher/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF (quantized), 775 downloads in 30 days
- second-state/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF (quantized), 666 downloads in 30 days
- lmstudio-community/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF (quantized), 323 downloads in 30 days
- backyardai/Llama-3.1-Nemotron-70B-Instruct-GGUF (quantized), 213 downloads in 30 days
- gaianet/Llama-3.1-Nemotron-70B-Instruct-HF-GGUF (quantized), 188 downloads in 30 days
- mlx-community/Llama-3.1-Nemotron-70B-Instruct-HF-bf16 (finetune), 188 downloads in 30 days
- unsloth/Llama-3.1-Nemotron-70B-Instruct-bnb-4bit (quantized), 178 downloads in 30 days
- MergekitCloud/mergekit-176 (merge), 155 downloads in 30 days
- DevQuasar-5/nvidia.Llama-3.1-Nemotron-70B-Instruct-HF-GGUF (quantized), 153 downloads in 30 days
Downloads by month
Downloads in the 30 days up to the end of each month, and the change from the month before.
| Month | Downloads | Change |
|---|---|---|
| Up to 2026-11-18 | 13,850 | +2% |
| October 2026 | 13,539 | -45% |
| September 2026 | 24,498 | +139% |
| August 2026 | 10,229 | -74% |
| July 2026 | 39,553 | +149% |
| June 2026 | 15,880 | +45% |
| May 2026 | 10,948 | -1% |
| April 2026 | 11,081 | -1% |
| March 2026 | 11,240 | -38% |
| February 2026 | 18,053 | +334% |
| January 2026 | 4,163 | -18% |
| December 2025 | 5,055 | -49% |
Its busiest 30 days so far ended on 2025-01-17, with 390,382 downloads.
Open nvidia/Llama-3.1-Nemotron-70B-Instruct-HF on Hugging Face
Sister project: Paper Pulse, the upvote history of every Hugging Face Daily Paper.