Does this model need a reasoning parser?

A model that thinks needs vLLM's --reasoning-parser to split that thinking out of the answer. Getting it wrong fails in two ways, and only one of them is visible.

Missing parser: the user sees the model's thinking in the reply — obvious, and quickly fixed. Wrong parser: it claims the entire output, the request finishes with stop, and content comes back empty. Nothing errors.

This reads the repo's chat template only — a few kilobytes, fetched from your browser — and asks the one question that decides it: does the assistant's turn carry a marker some parser closes on?

Why the family name cannot decide it

Two models from one family, one release apart, answer differently: Qwen3.6-35B-A3B emits <think> and needs the qwen3 parser; Qwen3-VL-30B emits nothing of the sort and is broken by it. A quantized pack inherits its source's template, so the same split runs through every repack of them.

The markers below were read out of vLLM's vllm/reasoning/ modules, not from documentation — a parser matches what its code matches. Only markers that discriminate a reasoning section are listed: an earlier version of this table included <|end|>, gpt-oss's turn terminator, and recommended a parser for a model that does no thinking at all.