Nvidia Just Released Llama Nemotron Ultra
4 by devaniranjan | 1 comments on Hacker News.
NVIDIA just released Llama 3.1 Nemotron Ultra (253B parameter model) that’s showing great performance on GPQA-Diamond, AIME, and LiveCodeBench. Their blog goes into detail but it shows up to 4x throughput over DeepSeek-R1 with better benchmarks. Blog: https://ift.tt/EncPAHm The model is available on HF and as a NIM. Has anyone tried it? HF: https://ift.tt/3JfFNeZ NIM: https://ift.tt/urPqx4T