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
- AI Infra Meme: While Countries Need TW-Scale Power for Datacenters, People Argue About Lightbulbs — mgostIH · 2026-10-27
- Legora runs 2,000 parallel agent evals on Modal Sandboxes for legal AI — blelbach · 2026-10-27
- Cloud release velocity scores: AWS 95, Azure 90, Google Cloud 82 — DavidLinthicum · 2026-10-27
- Selling a 5090 to scale local inference: one business weighs 5 hardware paths — Anarchaotic · 2026-10-27
- AWS tutorial: fleet-wide edge CV model lifecycle with SageMaker SDK v3, ~$0.07 per run — AWS ML Blog · 2026-10-27
- Qwen3.8-27B hits 40 tok/s on Jetson Thor with INT4 + MTP, accuracy beats FP16 — No-Dragonfly6246 · 2026-10-27