KRAFTON AI
A text-only 28.8B-total/4.3B-active MoE preview with native 262,144-token context and Apache 2.0 weights. Official 32GB NVFP4 use differs from MXFP8 offload; llama.cpp upstream support is pending. Publisher evaluations do not fill our three boards, and we have not run it.
Original model explanation ↗No comparable leaderboard score is included yet. Explore the evaluations and examples below.
Source comparison in the same chapter, not our matched-machine test
Following Wonder’s flagship capabilities leaves another Meta choice to examine: Glimmer, whose weights can be obtained for local deployment.
Official preview card, not our test
Official service docs, not applied for or called
This is our observation date, not an inferred launch date. The official card documents a 28.8B/4.3B text MoE preview under Apache 2.0; local deployment depends on quantization, runtime branch and hardware.
Checked source ↗