Running Local Models is Good Now
Vicki Boykis · blog · local-models, models
What it is — Local LLMs are now good enough for real agentic coding, not just toy queries.
Key points
- Roughly 75% of frontier accuracy/speed on agentic coding tasks.
- Tooling has matured — LM Studio, Ollama, containerised runs.
- Local gives introspection and control the API can’t.
💬 The room said — Dropped into an existing gripe about subscription costs - general take was that local models are tempting on paper, but the hardware outlay (people quoted $5-10k rigs) and cramped context windows keep it impractical for now.
Shared by Adam Tomat in #ai-dev.