The nvidia/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct galaxy

10 models are built on nvidia/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct: 10 quantized, 0 fine-tuned, 0 adapters and 0 merges. Together they were downloaded 5,554 times in the last 30 days.

Most downloaded direct derivatives

• mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-i1-GGUF (quantized), 1.4K downloads in 30 days
• bartowski/nvidia_Llama-3.1-8B-UltraLong-2M-Instruct-GGUF (quantized), 1.4K downloads in 30 days
• mradermacher/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct-i1-GGUF (quantized), 1.1K downloads in 30 days
• mradermacher/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct-GGUF (quantized), 408 downloads in 30 days
• mradermacher/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF (quantized), 371 downloads in 30 days
• DevQuasar-13/nvidia.Llama-3.1-8B-UltraLong-2M-Instruct-GGUF (quantized), 314 downloads in 30 days
• lmstudio-community/Llama-3.1-8B-UltraLong-2M-Instruct-GGUF (quantized), 141 downloads in 30 days
• itlwas/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct-Q4_K_M-GGUF (quantized), 39 downloads in 30 days
• Blasserman/Llama-3.1-Nemotron-8B-UltraLong-2M-Instruct-Q4_K_M-GGUF (quantized), 19 downloads in 30 days
• m-i/Llama-3.1-8B-UltraLong-2M-Instruct-mlx-8Bit (quantized), 15 downloads in 30 days

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