Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
dofm
79 days ago
|
parent
|
context
|
favorite
| on:
Gemma 4 QAT models: Optimizing compression for mob...
To briefly follow up, as of yesterday llama.cpp can do Gemma 4's MTP, so I have this working at least initially — details here:
https://hackertimes.com/item?id=48441450
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://hackertimes.com/item?id=48441450