Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
hrpnk
6 months ago
|
parent
|
context
|
favorite
| on:
Open models by OpenAI
With LM Studio you can configure context window freely. Max is 131072 for gpt-oss-20b.
coltonv
6 months ago
[–]
Yes but if I set it above ~16K on my 32gb laptop it just OOMs. Am I doing something wrong?
mekpro
6 months ago
|
parent
[–]
try enable flash attention and offload all layer to GPU
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: