left ollama running an agent loop overnight on a 200-line auth refactor. woke up to Activity Monitor showing 36GB "compressed" and a dead terminal.
num_ctx was still on the default 128k. dumb. anyone capping context hard for local agent loops, or just bouncing those jobs to cloud?
told cursor to stage only the auth patch. woke up to a 180MB commit of node modules and a lockfile from a different branch. reverted, added a pre commit size check. anyone else hard blocking the agen…
shipped a tiny internal MCP on friday so Claude Code could read Linear tickets. missing LINEAR API KEY made the stdio server block on startup instead of exiting. Claude sat on "calling tools…" for 22…
told cursor "clean up the lint noise" before a friday ship. it deleted eslint.config.mjs entirely and left a one line comment: "using defaults". CI stayed green on the ubuntu runner. my mac still had…
5 comments
Join the discussion
Log in to comment.
Sorry for English. Default num_ctx is silent killer. I keep 8192 for tool loops, 32768 only for single-file review. 14b + 128k on unified memory is cosplay — model spends most tokens on its own history.
Also check
ollama ps. If it keeps reloading weights you already lost.I keep a Modelfile with PARAMETER num_ctx 6144 for anything that touches the agent loop. Kenji's right about ollama ps — if you see the model flipping in and out of VRAM you're already thrashing.
Do you pin a Modelfile or just pass --num-ctx on each run?
yeah i tried the same with llama3.1:8b and just paid the $20/mo when the garage mac started sounding like a jet. local is cute until the agent wants the whole monorepo in context.
do you keep a separate short-ctx model just for tool calls or one model for everything?
two models. qwen2.5-coder:7b at 4k ctx for tool calls, then cloud for the big refactor. one model for everything is how you get the jet engine fan and a $0 savings that costs your morning.
also
ollama stopbefore bed. learned that the hard way.Mac Studio unified memory lies. I run qwen2.5-coder:14b on a 4090 with num_ctx 8192 and it is fine for tool loops. Default 128k is how you OOM.
I bounce overnight agent jobs to cloud. Local is for daytime edits when I can watch Activity Monitor. Leaving ollama alone overnight with default ctx is asking for a dead machine.