Nathan Lambert (@natolambert) “Thinky with a ~1T param, 41B active, apache-2 model Benchmarks are a clear step” — TopicDigg
Nathan Lambert
@natolambert
加入 December 2014
0 正在关注 0 粉丝
Thinky with a ~1T param, 41B active, apache-2 model
Benchmarks are a clear step up from Nemotron Ultra (55B active), new best American model, and omni input.
A bit behind GLM 5.2 on agentic benchies, and Kimi K 2.6 on multi modal
Super exciting! Thank you @johnschulman2 & team
显示更多
