Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
porphyra
77 days ago
|
parent
|
context
|
favorite
| on:
Qwen 3.6 27B is the sweet spot for local developme...
I think Atlas might also be slightly faster than vLLM:
https://flowtivity.ai/blog/120-tok-s-1m-context-private-ai-d...
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
https://flowtivity.ai/blog/120-tok-s-1m-context-private-ai-d...