Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
kerenskiy
7 days ago
|
parent
|
context
|
favorite
| on:
LFM2.5-24B-A2B: Built for fast on-device agents
The context window fills up also/mostly from prefil which is supposed to be 20+ times faster or so. I think 40-80 tps for decode/output is believable for claude models
help
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: