Local AI Coding on a 16GB GPU: Strata, OpenCode, and Qwen3.8
Run a local coding agent with Strata and OpenCode. Examine reported RTX 4060 Ti results, RAM requirements, prompt reuse, reasoning budgets, and the limits of replacing a paid subscription.
Other Posts Tagged "Self Hosted AI"
OpenCode vs Claude Code: 2026 Coding Agent Comparison
Compare OpenCode and Claude Code across model choice, local inference, pricing, permissions, project instructions, and daily coding workflows.
Llama 3.1 8B and Qwen3.8 27B GPU Benchmarks on Vast.ai
Measured Ollama benchmarks of Llama 3.1 8B and Qwen3.8 27B across leading Vast.ai GPUs. Compare decode speed, long-context behavior, rental cost, self-hosting tradeoffs, API credits, and subscriptions.
Building a Privacy-Preserving AI Assistant for Meshtastic
A practical account of building a local AI assistant for Meshtastic, with private configuration, queued TCP access, retrieval tools, and a safer dashboard.
