Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
numeri
5 days ago
|
parent
|
context
|
favorite
| on:
Mercury 2: Fast reasoning LLM powered by diffusion
but Taalas had to quantize Llama 3.1 8B to death to get it to fit. It can't produce coherent non-English text at all.
help
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: