The story’s score and claims

Comments on No. 85 of 122 · Empero · edition of Tuesday 17 November 2026

Quark: Our whole training stack, end to end, for $4,200

Summary

Empero AI released Quark, a 165M-parameter language model it says it trained end to end for about $4,200 of compute, covering data, pretraining, 128K-context extension and reinforcement learning.

Comments

Ranked by a public rubric, not by votes: what a comment adds counts, not who wrote it. How comments are ranked · Comment rules