specific method · filed under inference & serving
Task- and mode-specific sampling parameter recommendations
Recommended sampling parameters vary according to the selected mode and task type.
- source
- 1
- model
- 1
- lab adopt it
- 1
- strongest
- optional
How sources treat it
One count per evidence span, weakest treatment to strongest.
optional 2
Documented in
Evidence
2 spans quoted from the sources, strongest treatment first.
We suggest using the following sets of sampling parameters depending on the mode and task type:
optionalinference servingin Qwen3.5-35B-A3BQwen
We suggest using the following sets of sampling parameters depending on the mode and task type
optionalinference servingin Qwen3.5-35B-A3BQwen
Filed alongside
Other methods under inference & serving :: reasoning control.
Configurable reasoning effortChain-of-thought reasoningDefault thinking modeDeployment-time scalar effort controlDisabling reasoning via chat-template configurationInference-time reasoning budget controlInterleaved thinking between tool callsThinking mode selectionCross-turn persistent reasoning historyMaximum thinking effortReasoning parserAlways-on thinking modeclear_thinking chat-template parameterControl-token-enabled thinking modeEffort-dependent exponential token-penalty scheduleGenerate-verify-refine loopMedium-effort reasoning modeParallel-fewest-step samplingQwen3 soft thinking switchTest-time compute scalingAdaptive reasoningCapped linear reasoning-token length deductionConfigurable thinking or reasoning modeControllable thinking effort via system message and per-token cost