Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
janderland
24 days ago
|
parent
|
context
|
favorite
| on:
AI subscriptions are a ticking time bomb for enter...
Has Kimi found a way to vastly reduce the amount of VRAM required without running at 3 tokens per second? That’s the real concern.
dools
24 days ago
[–]
I said "open weight" rather than "local". I mean, local if you have $240k to drop on GPUs but you can run Kimi k2.6 on a B300 cluster for ~$50/hour too.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
