Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
pama
27 days ago
|
parent
|
context
|
favorite
| on:
Why your local LLM feels dumber than it is
No favorite in single spark usage really. Glimmer is interesting because it scales well under load. Qwen3.6 MoE was fast enough on low concurrency. Qwen3.8 works but slower than the DS flash on the two sparks.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: