Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
starik36
7 months ago
|
parent
|
context
|
favorite
| on:
Gemma 3 QAT Models: Bringing AI to Consumer GPUs
On an A5000 with 24GB, this model typically gets between 20 to 25 tps.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: