Kimi-K3 is estimated at 50.4B active params, with 2.8T models needing 8 B200s
StefanoGogioso · x · 2026-07-23
Kimi-K3 active params are estimated at 50.4B, with bigger next-gen models expected
A post claims Kimi-K3 has 50.4B active parameters, which would make it roughly 25% slower than GLM under the same setup.
It also speculates that Zhipu's next foundation model could reach 1.5T parameters, and notes that a 2.8T-parameter model would require 8× B200/B300 in NVFP4 to run.
More from Infra
- Alchemy beta expands to 204 AWS services, ECS/EKS, and Lambda workflows — samgoodwin89 · 2026-07-23
- Ten tactics to cut AI API bills by up to 90% without shrinking output — socialwithaayan · 2026-07-23
- Why AI pricing is really a memory-and-infrastructure problem, not just tokens — Kyrannio · 2026-07-23
- Open-source webfetch cuts agent search tokens by 87% and cost by 66% — Remote-Breadfruit204 · 2026-07-23
- NVIDIA launches Jetson Thor T2000 and T3000 for robotics and edge AI — NVIDIAAI · 2026-07-23
- AWS is said to ship 2.4 million Trainium3 accelerators this year — Beth_Kindig · 2026-07-23