I pointed three coding CLIs at the same local model and ran twelve tasks through each one. The model was Qwen 35B, hosted on an RTX 4070 12GB via llama-server with --cpu-moe . The tasks were mundane: build a hello.
Source: [Dev.to](https://dev.to/kenimo49/qwen-code-vs-aider-vs-opencode-i-ran-the-same-12-tasks-through-3-local-cli-agents-on-one-rtx-4070-378i)