awesome-local-ai: one-command installers for tested local LLM + coding agent setups
julianharris · x · 2026-09-05
The GitHub repo awesome-local-ai curates tested pairings of models, hardware and inference stacks for running capable LLMs locally, with one-command installers:
- Ubuntu + RTX 4090 24GB: llama.cpp + unsloth 4-bit running Qwen 27b
- Mac 128GB: MTPLX 2.11 with its custom kernel (Flash-Next)
- Mac 64GB: Qwen 27b on MTPLX
Models are served via an OpenAI-compatible API with a coding agent (opencode) already wired up. All perf/memory figures were measured on real hardware. ./install.sh picks a combo for your machine; ./start.sh starts/stops the server on demand.
Related event: awesome-local-ai: One-Command Local LLM Plus Coding Agent Setups(2 posts)→
More from coding & agent
- OpenAI ships GPT-6 Astra with three new agent-building API updates — gabrielchua · 2026-09-05
- Hamel Husain: Hard-to-eval products are bad products — and AI makes data science more valuable — hugobowne · 2026-09-05
- seq-mcp: An MCP Server Giving AI Agents Controlled Read Access to Seq Logs — modelcontextprotocol · 2026-09-05
- Crew: An MIT-Licensed Desktop App Where Multiple LLM CLIs and People Share One Project — Classic-Grab-2866 · 2026-09-05
- Why agents name folders zz: reverse alphabetical tool ordering surfaces messages first — morqon · 2026-09-05
- After AI wrote his whole Python package, he asks: how can we ever trust AI code in production? — Lukee67 · 2026-09-05