The same num_ctx 16384 sent at the JSON root loads a 4096-token context, while the same value inside options loads 16384 — both requests return HTTP 200.
LLM

Ollama returns 200 and loads a 4096 context when num_ctx sits outside « options »

/

Ollama’s /api/generate drops num_ctx and num_predict placed at the JSON root: HTTP 200, plausible answer, default 4096 context. ollama ps shows the truth.