News
Newest
Ask
Show
Jobs
Open on GitHub
Show HN: Which Mac runs which LLM, and how fast
(macyou.co)
11 points | by
bagdaerdev
1 hour ago
4 comments
cmdrmac
23 minutes ago
How is this tool better than llmfit? It doesn’t have many of the newer models.
lreeves
27 minutes ago
These seems really out of date, Qwen 3.8 Flash Next and the prior 3.8 stuff is pretty state of the art for local usage and there's nothing? Default is Llama 3.3?? Come on.
StilesCrisis
28 minutes ago
I'm super interested in this topic. Unfortunately, the page is just Claude slop with no real answers.
[-]
spwa4
5 minutes ago
Use the omlx community benchmarks:
https://omlx.ai/benchmarks/performance
bagdaerdev
1 hour ago
[dead]
https://omlx.ai/benchmarks/performance