Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
sureglymop
on Jan 28, 2025
|
parent
|
context
|
favorite
| on:
Promising results from DeepSeek R1 for code
This didn't work well for me, no changes are ever made but maybe it's because I'm just using the 14B model.
manmal
on Jan 28, 2025
[–]
In case you are on a 32+GB Mac, you could try deepseek-r1-distill-qwen-32b-mlx in LM Studio. It’s just barely usable speed-wise, but gives useful results most of the time.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search: