Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hedgehog
5 months ago
|
parent
|
context
|
favorite
| on:
Mistral AI Launches New 8x22B MOE Model
Ollama (which wraps llama.cpp) supports splitting a model across devices so you get some acceleration even on models too big to fit entirely in GPU memory.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: