New model released by Nvidia available here: https://huggingface.co/chat/ it’s said that it has better performance than 4o or Claude 3.5 Sonnet (https://github.com/lmarena/arena-hard-auto). Also available in ollama:
ollama run nemotronAnd it counts strawberry R letter correctly 🙂
Bonus: can be run with 2 MBP with Exo and MLX:
Exo can be installed from here: https://github.com/exo-explore/exo it can be distributed across multiple devices and systems dramatically decrease hardware costs for home/personal testing.