How do I disable thinking for gemma4 in ollama?

<!-- SC_OFF --><div class="md"><p>I run the same model: `google_gemma-4-E2B-it-IQ3_M.gguf` with lmstudio or llama-server</p> <p>and I connect thru `/v1/chat/completions` EP.</p>

<!-- SC_OFF --><div class="md"><p>I like to be able to enable and disable thinking using a system prompt, so that I can control what which prompts generate thinking tokens rather

<!-- SC_OFF --><div class="md"><p>I can't get my model to think. According to the <a href="https://huggingface.co/google/gemma-4-31B">documentation</a>, thinking should be

<!-- SC_OFF --><div class="md"><p>I am running <code>unsloth/gemma-4-26B-A4B-it-GGUF/gemma-4-26B-A4B-it-UD-Q4_K_XL.gguf</code> with llama-server (with reasoning enabled). </p>

<!-- SC_OFF --><div class="md"><p>Beginner here, now I have a good GPU and ollama using docker. Pulled the Gemma4 weights and was able to add it to cursor using ngrok. </p>

<!-- SC_OFF --><div class="md"><p>Hi,</p> <p>has anybody succeeded in running llama.cpp with Gemma 31b dense and Gemma e4b as draft model, and simultaneously inhibit the voice

<!-- SC_OFF --><div class="md"><p>I've got the model Qwen3.6-35B-A3B-4bit running in oMLX, and I want to enable the kwarg preserve_thinking as described here: <a