TheFocus Labs
Back issues Current issue
← Workshop

Q3 2026

Workshop

Things to try — copy-paste procedures, MCP setup, prompts.

  • August 17, 2026

    whichllm: pick a local model that is actually fast

    whichllm ranks the best local models for your hardware — general, coding, vision, math — then whichllm run downloads the top pick and starts a chat. --speed fast keeps only the ones estimated at 30+ tok/s.

The HarnessField NotesDrive
Published by TheFocus.AI Courses · Standards · Source
Don't miss out

Stay ahead of the curve.

Field reports from AI engineering — what's shipping, what's breaking, what's about to change. One email per issue.