wow antirez does not sleep
H3-metal – Native MiniMax-H3 inference for Apple Silicon
11–20 of 108 posts
Understatement of the year :-D
Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#12wow antirez does not sleep
when you have enough money to not have to worry about anything, you can go back to your hobbies. in this case, his hobby is programming.
Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#13Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#14Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#15I'd love to know what the alternatives are and how this is better
Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#16[dead]
Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#17Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#18Earlier quoted context omitted.
when you have enough money to not have to worry about anything, you can go back to your hobbies. in this case, his hobby is programming.
Being a world class talent is independent of financial situation.
talent w/o financial stability is a battery w/o circuit.
Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#19wow antirez does not sleep
Wow, had to check some of his other repos; his the one behind dump1090
Re: H3-metal – Native MiniMax-H3 inference for Apple Silicon
#20I've been using MiniMax H3 on my M5 Pro 64GB MacBook Pro through ComfyUI. It works extremely well. I had to modify the default ComfyUI workflows to use a GGUF quant (city96's ComfyUI-GGUF custom node, UnetLoaderGGUF in place of the stock loader) [0]. I use the model labeled Q5_K_M. There is Q8_0 available as well, which is 34GB and fits fine in 64GB unified memory if you keep resolution modest. The main issue is spee…
I wonder how much faster your m5 pro is compared to my M1 Max @ 64gb