Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
jburgess777
14 days ago
|
parent
|
context
|
favorite
| on:
Run Qwen 3.8 Flash Next (125B) on consumer hardwar...
The smallest I have seen is DeepSeek 4.1 flash at 890 bytes per token.
londons_explore
13 days ago
[–]
I suspect that commercial labs have unpublished work lowering this further. It's the obvious thing to optimise for when RAM is so expensive and you have a lot of users.
reply
Consider applying for YC's Winter 2027 batch!
Applications
are open till November 2.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
