Blog

Building for Autonomy

Thoughts on agent-first infrastructure, self-hosted systems, and owning the stack.

Filtering by: Engineering × Clear
#machin #ai-agents #ai-engineering #compiler #open-source #self-hosted #a2a #agent-first #automaintainer #cli #devtools #inference #infrastructure #llm #mago #performance #supercli #ai #analytics #architecture #autonomous-maintenance #bootstrappers #byok #chatbot #chatsnip #ci-cd #concurrency #creativity #crm-cli #crmd
Engineering · July 2026

A 7-billion-parameter LLM at the speed of a 1B — in pure MFL

I ran OLMoE-1B-7B — a 7-billion-parameter Mixture-of-Experts model — in pure MFL, token-identical to the fp32 reference, streamed from disk, at 14.5 tok/s on a laptop. The disruption wasn't in the engine; it was in the model.

#machin #llm #moe #inference #pure-mfl
Read more