Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
storus
3 months ago
|
parent
|
context
|
favorite
| on:
Apple M5 chip
M5 is supposed to support FP4 natively which would explain the speed up on Q4 quantized models (down from BF16).
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
