Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
zht
10 months ago
|
parent
|
context
|
favorite
| on:
Kimi K2 Thinking, a SOTA open-source trillion-para...
It’s kinda misleading to omit the generally terrible prompt processing speed on Macs
30 tokens per second looks good until you have to wait minutes for the first token
simonw
10 months ago
[–]
The tweet I linked to includes that information in the chart.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
30 tokens per second looks good until you have to wait minutes for the first token