Local Agents Are Not Toys | matgreten.dev
https://matgreten.dev/posts/local-agents-are-not-toys/ ↗Benchmark results from an M5 Max Mac show that local LLMs running via Ollama and OpenCode — particularly the 35B Qwen 3.6 MoE model — are fast and reliable enough for bounded agentic tasks, though not replacements for cloud models.