Docker Model Runner vs Ollama: Should You Switch? (RTX 4090)
Docker Model Runner vs Ollama on an RTX 4090: 70–90 tok/s on 7–8B models, a 40–60 minute first DMR setup, and why my agent’s JSON parsing broke.
Docker Model Runner vs Ollama on an RTX 4090: 70–90 tok/s on 7–8B models, a 40–60 minute first DMR setup, and why my agent’s JSON parsing broke.
IntelliJ sync failing with “Could not run phased build action”? Mine failed 6–7 times until ./gradlew –version showed JVM 11 under a Java 17 project.
Codex CLI edits files but npm install hangs or fails? workspace-write keeps network access off. How to confirm it, three ways past it, and the one I use.
Codex ran out of room mid-refactor? I ran /compact once, re-pinned five facts, then moved to /new and finished the last modules in under two hours.