alt Hacker NewsM5 air here with 32gb ram and 10/10 cores. Anyone got some luck with mlx builds on oMLX so far? Not at my machine right now and would love to know if these models already work including tool calling
Replies
smith7018 • today at 2:25 PM
I know that someone got Gemma 4 E4B working with MLX [1] but I don't know much more than that.
The latest release v0.3.2 has partial support, generation is supported but not all special tokens are handled. I've done some personal testing to add tool calling and <|channel> thinking support. https://github.com/Yukon/omlx