jamesarslan/local-ai-coding-setup
Local AI coding pipeline on an RTX 5090: llama.cpp, Qwen3.5/3.6 MoE, Gemma 4, TurboQuant KV, OpenCode, Claude Code, MCP. 188 t/s (Qwen3.5-35B-A3B, mainline, f16 KV); ~177 t/s (Qwen3.6-35B-A3B, turbo3, TLA=2). Optional cloud GPU server; default config uses hosted Context7 docs MCP.
GitHub repository with 20 stars and 4 forks.
Language: Shell
Topics: ai-coding, claude-code, gemma, inference, llama-cpp, local-llm, mcp, opencode, qwen, rtx-5090