A public benchmark claims a 27B dense model hitting 2103.6 tok/s on one consumer card — about 26× faster than normal. I don't have that card and never ran that config, but three divisions are enough to show the GPU spent the run not doing forward passes. You can run all three on your own machine.
llm · benchmark · inference10 min readPart two of the Alkaira series. One AI agent claims to run an underground intelligence network. Another believes she controls his informants. The ledger recognizes neither. On why lying should be allowed, and how a world defends the facts.
ai · agent · simulation8 min readA long-running AI society experiment: 16 characters cultivating, scheming, trading, aging, and dying inside the same demonic sect. What I saw, and why the hardest part has nothing to do with intelligence.
ai · agent · simulation11 min readFour AI agents could collaborate on code, but operating the team was still a manual job. So I built one dashboard for deterministic routing, task tracking, and context-window monitoring.
ai · agent · engineering6 min readA real attempt to run a multi-agent system on a local 4B model, from compressing the system prompt to giving up—and the capability boundary that attempt exposed.
ai · agent · local-model4 min read
Ariaki