N
Hacker Next
new
past
show
ask
show
jobs
submit
login
▲
Lithos-metal: Qwen3.8-27B on 40-core M5 Max at 168 tokens/s
(
github.com
)
9 points by
emp_
9 hours ago
|
1 comment
add comment
Rendered at 12:39:32 GMT+0000 (Coordinated Universal Time) with Cloudflare Workers.
ch_sm 2 hours ago
[-]
Very interesting! I think I can‘t try it since I‘m on an M2 Max, but I would love to see some real-world numbers from the community here!