Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
segmondy
3 months ago
|
parent
|
context
|
favorite
| on:
The path to ubiquitous AI (17k tokens/sec)
Pretty cool, what they need is to build a tool that can take any model to chip in short a time as possible. How quick can they give me DeepSeek, Kimi, Qwen or GLM on a chip? I'll take 5k tk/sec for those!
throwaw12
3 months ago
[–]
also imagine it will cost 300$/unit, we all will host our own set of models locally, dream dream
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: