Hacker Times
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
gavmor
3 months ago
|
parent
|
context
|
favorite
| on:
Accelerating Gemma 4: faster inference with multi-...
Take a look at
https://chatjimmy.ai/
-- it's running against Taalas' "hardcore" silicon model, ie a dedicated, ASIC-like chip.
bikelang
3 months ago
|
next
[–]
Wow - actually pretty astonishing how fast their inference is. So fast it feels fake?
qingcharles
3 months ago
|
parent
|
next
[–]
Yeah, when you find fast inference like that it almost feels like the answer arrives before you hit return. Now imagine it running locally with no server round-trip.
jiggawatts
3 months ago
|
prev
[–]
Sure it's fast, but it's at ChatGPT 2.0 levels of intelligence.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
