/AI2d ago

Developer Runs 519B Kimi Model Locally at 262K Context

--0--
Original posts
Reposts
Original postclem 馃#68
0xSero@0xSero

6 months ago I said I won't stop until I have Kimi at home, after 10+ botched REAPs I finally have it

Needs benchmarking of course.

- 45 tok/s decode - 954 tok/s prefill no cache - 95k+ tok/s cached prefill - 262k context - 360gb full context

https://huggingface.co/0xSero/Kimi-K2.6-519B-NVFP4

2:51 PM 路 Jun 1, 2026 路 33.5K Views
Sentiment
Sentiment building, check back later.
Cluster Engagement
-
Views
-
Comments
-
Reposts
-
Bookmarks
Expand data
Posts from X
Most Activity
Most ActivityTimeline
No ranked X posts are available for this story yet.