README could clearly make use of a cleanup, seems to be more like a session log dump now than a good introduction to the project for a new user. Maybe try something like "Remove anything from the README.md that wouldn't be helpful to someone who sees this project with zero context, for the first time. Rewrite all paragraphs and sections to be concise and remove all fluff, leave only important details new users must know before using the project".
Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
21–30 of 126 posts
Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#22how much energy does it consume?
Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#23Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#24Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#25Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#26Folks talking about how 32G is not enough for local use, but then there's been work like this to empower it.
My hope is that the new 32G M6 will be "useful" locally, possibly because of work like this.
Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#27Earlier quoted context omitted.
I'm sorry this makes it seem like I didn't do my research. I did a TON. To fix it I'll add a benchmark/comparison table. Also, I wouldn't call it market research since this is not commercial AT ALL.
Hey Carlos, thanks for sharing with the community! Appreciated
Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#28It seems we could use a new kind of memory that streams the weight data in, like GDDR in reverse.
Re: Show HN: Running 104GB Qwen3.8-Flash-Next on 48GB Mac with at ~12 tok/s
#29Earlier quoted context omitted.
> every implementation idea rediscovered five times and wrapped in a new README That's open source since forever, unfortunately.
It's what happens when you don't do market research.