Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
tamlin
9 months ago
|
parent
|
context
|
favorite
| on:
Running DeepSeek R1 Models Locally on NPU
Yes, agree. Probably the main thing is the NPU is just a dedicated unit without the generality / complexity of a CPU and so able to crunch matmuls more efficiently.
Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
