Joshua Warren(@JoshuaSWarren):Credit where it's due: MiniMax H3 is the model. The engine is @ashxhart's TensorFold, with H3 support by @u1tra_instinct and the MLX port from @pipenetwork and @AIBizarrothe. My part: the Linux on Apple Silicon port. The int8 weights are on Hugging Face:

Joshua Warren

@JoshuaSWarren

Omarchy M team. Making Apple Silicon fast under Linux: MLX, Mesa GPU, Neural Engine. Shipped an iPhone app with no Mac. Building Remnic.

参加 May 2011

6.4K フォロー中 9K ファン

Joshua Warren@JoshuaSWarren

2026.10.09 14:17

Credit where it's due: MiniMax H3 is the model. The engine is @ashxhart's TensorFold, with H3 support by @u1tra_instinct and the MLX port from @pipenetwork and @AIBizarrothe. My part: the Linux on Apple Silicon port. The int8 weights are on Hugging Face: